Upload folder using huggingface_hub
Browse files
.summary/0/events.out.tfevents.1736359633.169ba1db2e67
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b56018a412bfdd08a5373b3707f9cc88a417b55d1d74d9cb0fc78daf0aaa7426
|
| 3 |
+
size 98803
|
README.md
CHANGED
|
@@ -15,7 +15,7 @@ model-index:
|
|
| 15 |
type: doom_health_gathering_supreme
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
-
value:
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
@@ -38,19 +38,19 @@ python -m sample_factory.huggingface.load_from_hub -r jdollman/rl_course_vizdoom
|
|
| 38 |
|
| 39 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
| 40 |
```
|
| 41 |
-
python -m .
|
| 42 |
```
|
| 43 |
|
| 44 |
|
| 45 |
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
|
| 46 |
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
| 47 |
-
|
| 48 |
## Training with this model
|
| 49 |
|
| 50 |
To continue training with this model, use the `train` script corresponding to this environment:
|
| 51 |
```
|
| 52 |
-
python -m .
|
| 53 |
```
|
| 54 |
|
| 55 |
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
| 56 |
-
|
|
|
|
| 15 |
type: doom_health_gathering_supreme
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
+
value: 3.66 +/- 0.61
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
|
|
| 38 |
|
| 39 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
| 40 |
```
|
| 41 |
+
python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
|
| 42 |
```
|
| 43 |
|
| 44 |
|
| 45 |
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
|
| 46 |
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
| 47 |
+
|
| 48 |
## Training with this model
|
| 49 |
|
| 50 |
To continue training with this model, use the `train` script corresponding to this environment:
|
| 51 |
```
|
| 52 |
+
python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
|
| 53 |
```
|
| 54 |
|
| 55 |
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
| 56 |
+
|
checkpoint_p0/best_000000060_245760_reward_4.509.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cac643956874e4a4474fe4878548f2a9474aabb621f9db8839d97117ca4b071
|
| 3 |
+
size 34929051
|
checkpoint_p0/checkpoint_000000064_262144.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f4528818f31e4c3a4ec8b98817951386c267afd6c3069efba7ab35cad123d12
|
| 3 |
+
size 34929477
|
checkpoint_p0/checkpoint_000000104_425984.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c64b9c81dbbe73e51cbc113eac9925ada149ef488f60640bf03f8869624a0b
|
| 3 |
+
size 34929477
|
config.json
CHANGED
|
@@ -46,6 +46,8 @@
|
|
| 46 |
"learning_rate": 0.0001,
|
| 47 |
"lr_schedule": "constant",
|
| 48 |
"lr_schedule_kl_threshold": 0.008,
|
|
|
|
|
|
|
| 49 |
"obs_subtract_mean": 0.0,
|
| 50 |
"obs_scale": 255.0,
|
| 51 |
"normalize_input": true,
|
|
@@ -136,6 +138,5 @@
|
|
| 136 |
"train_for_env_steps": 4000000
|
| 137 |
},
|
| 138 |
"git_hash": "unknown",
|
| 139 |
-
"git_repo_name": "not a git repository"
|
| 140 |
-
"train_script": ".usr.local.lib.python3.10.dist-packages.colab_kernel_launcher"
|
| 141 |
}
|
|
|
|
| 46 |
"learning_rate": 0.0001,
|
| 47 |
"lr_schedule": "constant",
|
| 48 |
"lr_schedule_kl_threshold": 0.008,
|
| 49 |
+
"lr_adaptive_min": 1e-06,
|
| 50 |
+
"lr_adaptive_max": 0.01,
|
| 51 |
"obs_subtract_mean": 0.0,
|
| 52 |
"obs_scale": 255.0,
|
| 53 |
"normalize_input": true,
|
|
|
|
| 138 |
"train_for_env_steps": 4000000
|
| 139 |
},
|
| 140 |
"git_hash": "unknown",
|
| 141 |
+
"git_repo_name": "not a git repository"
|
|
|
|
| 142 |
}
|
replay.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82dfafed4156f792199d5eba9bc9c6b287f1da51f4aa0f0347d8c11a759e4366
|
| 3 |
+
size 5206387
|
sf_log.txt
ADDED
|
@@ -0,0 +1,823 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[2025-01-08 18:07:19,496][01481] Saving configuration to /content/train_dir/default_experiment/config.json...
|
| 2 |
+
[2025-01-08 18:07:19,498][01481] Rollout worker 0 uses device cpu
|
| 3 |
+
[2025-01-08 18:07:19,499][01481] Rollout worker 1 uses device cpu
|
| 4 |
+
[2025-01-08 18:07:19,501][01481] Rollout worker 2 uses device cpu
|
| 5 |
+
[2025-01-08 18:07:19,502][01481] Rollout worker 3 uses device cpu
|
| 6 |
+
[2025-01-08 18:07:19,503][01481] Rollout worker 4 uses device cpu
|
| 7 |
+
[2025-01-08 18:07:19,504][01481] Rollout worker 5 uses device cpu
|
| 8 |
+
[2025-01-08 18:07:19,505][01481] Rollout worker 6 uses device cpu
|
| 9 |
+
[2025-01-08 18:07:19,506][01481] Rollout worker 7 uses device cpu
|
| 10 |
+
[2025-01-08 18:07:19,660][01481] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 11 |
+
[2025-01-08 18:07:19,662][01481] InferenceWorker_p0-w0: min num requests: 2
|
| 12 |
+
[2025-01-08 18:07:19,697][01481] Starting all processes...
|
| 13 |
+
[2025-01-08 18:07:19,699][01481] Starting process learner_proc0
|
| 14 |
+
[2025-01-08 18:07:19,744][01481] Starting all processes...
|
| 15 |
+
[2025-01-08 18:07:19,753][01481] Starting process inference_proc0-0
|
| 16 |
+
[2025-01-08 18:07:19,753][01481] Starting process rollout_proc0
|
| 17 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc1
|
| 18 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc2
|
| 19 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc3
|
| 20 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc4
|
| 21 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc5
|
| 22 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc6
|
| 23 |
+
[2025-01-08 18:07:19,755][01481] Starting process rollout_proc7
|
| 24 |
+
[2025-01-08 18:07:39,083][03278] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 25 |
+
[2025-01-08 18:07:39,093][03285] Worker 5 uses CPU cores [1]
|
| 26 |
+
[2025-01-08 18:07:39,089][03278] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
| 27 |
+
[2025-01-08 18:07:39,101][03282] Worker 1 uses CPU cores [1]
|
| 28 |
+
[2025-01-08 18:07:39,193][03278] Num visible devices: 1
|
| 29 |
+
[2025-01-08 18:07:39,287][03265] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 30 |
+
[2025-01-08 18:07:39,296][03265] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
| 31 |
+
[2025-01-08 18:07:39,299][03279] Worker 2 uses CPU cores [0]
|
| 32 |
+
[2025-01-08 18:07:39,305][03281] Worker 3 uses CPU cores [1]
|
| 33 |
+
[2025-01-08 18:07:39,333][03265] Num visible devices: 1
|
| 34 |
+
[2025-01-08 18:07:39,357][03265] Starting seed is not provided
|
| 35 |
+
[2025-01-08 18:07:39,358][03265] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 36 |
+
[2025-01-08 18:07:39,359][03265] Initializing actor-critic model on device cuda:0
|
| 37 |
+
[2025-01-08 18:07:39,360][03265] RunningMeanStd input shape: (3, 72, 128)
|
| 38 |
+
[2025-01-08 18:07:39,363][03265] RunningMeanStd input shape: (1,)
|
| 39 |
+
[2025-01-08 18:07:39,404][03265] ConvEncoder: input_channels=3
|
| 40 |
+
[2025-01-08 18:07:39,418][03283] Worker 4 uses CPU cores [0]
|
| 41 |
+
[2025-01-08 18:07:39,446][03284] Worker 6 uses CPU cores [0]
|
| 42 |
+
[2025-01-08 18:07:39,499][03280] Worker 0 uses CPU cores [0]
|
| 43 |
+
[2025-01-08 18:07:39,619][03286] Worker 7 uses CPU cores [1]
|
| 44 |
+
[2025-01-08 18:07:39,658][01481] Heartbeat connected on Batcher_0
|
| 45 |
+
[2025-01-08 18:07:39,664][01481] Heartbeat connected on InferenceWorker_p0-w0
|
| 46 |
+
[2025-01-08 18:07:39,670][01481] Heartbeat connected on RolloutWorker_w0
|
| 47 |
+
[2025-01-08 18:07:39,673][01481] Heartbeat connected on RolloutWorker_w1
|
| 48 |
+
[2025-01-08 18:07:39,676][01481] Heartbeat connected on RolloutWorker_w2
|
| 49 |
+
[2025-01-08 18:07:39,679][01481] Heartbeat connected on RolloutWorker_w3
|
| 50 |
+
[2025-01-08 18:07:39,684][01481] Heartbeat connected on RolloutWorker_w4
|
| 51 |
+
[2025-01-08 18:07:39,688][01481] Heartbeat connected on RolloutWorker_w5
|
| 52 |
+
[2025-01-08 18:07:39,693][01481] Heartbeat connected on RolloutWorker_w6
|
| 53 |
+
[2025-01-08 18:07:39,713][01481] Heartbeat connected on RolloutWorker_w7
|
| 54 |
+
[2025-01-08 18:07:39,938][03265] Conv encoder output size: 512
|
| 55 |
+
[2025-01-08 18:07:39,939][03265] Policy head output size: 512
|
| 56 |
+
[2025-01-08 18:07:40,004][03265] Created Actor Critic model with architecture:
|
| 57 |
+
[2025-01-08 18:07:40,005][03265] ActorCriticSharedWeights(
|
| 58 |
+
(obs_normalizer): ObservationNormalizer(
|
| 59 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
| 60 |
+
(running_mean_std): ModuleDict(
|
| 61 |
+
(obs): RunningMeanStdInPlace()
|
| 62 |
+
)
|
| 63 |
+
)
|
| 64 |
+
)
|
| 65 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
| 66 |
+
(encoder): VizdoomEncoder(
|
| 67 |
+
(basic_encoder): ConvEncoder(
|
| 68 |
+
(enc): RecursiveScriptModule(
|
| 69 |
+
original_name=ConvEncoderImpl
|
| 70 |
+
(conv_head): RecursiveScriptModule(
|
| 71 |
+
original_name=Sequential
|
| 72 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
| 73 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
| 74 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
| 75 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
| 76 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
| 77 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
| 78 |
+
)
|
| 79 |
+
(mlp_layers): RecursiveScriptModule(
|
| 80 |
+
original_name=Sequential
|
| 81 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
| 82 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
| 83 |
+
)
|
| 84 |
+
)
|
| 85 |
+
)
|
| 86 |
+
)
|
| 87 |
+
(core): ModelCoreRNN(
|
| 88 |
+
(core): GRU(512, 512)
|
| 89 |
+
)
|
| 90 |
+
(decoder): MlpDecoder(
|
| 91 |
+
(mlp): Identity()
|
| 92 |
+
)
|
| 93 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
| 94 |
+
(action_parameterization): ActionParameterizationDefault(
|
| 95 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
| 96 |
+
)
|
| 97 |
+
)
|
| 98 |
+
[2025-01-08 18:07:40,493][03265] Using optimizer <class 'torch.optim.adam.Adam'>
|
| 99 |
+
[2025-01-08 18:07:46,990][03265] No checkpoints found
|
| 100 |
+
[2025-01-08 18:07:46,990][03265] Did not load from checkpoint, starting from scratch!
|
| 101 |
+
[2025-01-08 18:07:46,990][03265] Initialized policy 0 weights for model version 0
|
| 102 |
+
[2025-01-08 18:07:46,995][03265] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 103 |
+
[2025-01-08 18:07:47,002][03265] LearnerWorker_p0 finished initialization!
|
| 104 |
+
[2025-01-08 18:07:47,004][01481] Heartbeat connected on LearnerWorker_p0
|
| 105 |
+
[2025-01-08 18:07:47,091][03278] RunningMeanStd input shape: (3, 72, 128)
|
| 106 |
+
[2025-01-08 18:07:47,092][03278] RunningMeanStd input shape: (1,)
|
| 107 |
+
[2025-01-08 18:07:47,104][03278] ConvEncoder: input_channels=3
|
| 108 |
+
[2025-01-08 18:07:47,221][03278] Conv encoder output size: 512
|
| 109 |
+
[2025-01-08 18:07:47,221][03278] Policy head output size: 512
|
| 110 |
+
[2025-01-08 18:07:47,277][01481] Inference worker 0-0 is ready!
|
| 111 |
+
[2025-01-08 18:07:47,279][01481] All inference workers are ready! Signal rollout workers to start!
|
| 112 |
+
[2025-01-08 18:07:47,482][03286] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 113 |
+
[2025-01-08 18:07:47,483][03285] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 114 |
+
[2025-01-08 18:07:47,485][03281] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 115 |
+
[2025-01-08 18:07:47,489][03282] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 116 |
+
[2025-01-08 18:07:47,498][03284] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 117 |
+
[2025-01-08 18:07:47,495][03283] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 118 |
+
[2025-01-08 18:07:47,499][03279] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 119 |
+
[2025-01-08 18:07:47,505][03280] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 120 |
+
[2025-01-08 18:07:48,462][03284] Decorrelating experience for 0 frames...
|
| 121 |
+
[2025-01-08 18:07:48,463][03283] Decorrelating experience for 0 frames...
|
| 122 |
+
[2025-01-08 18:07:48,820][01481] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 123 |
+
[2025-01-08 18:07:48,839][03283] Decorrelating experience for 32 frames...
|
| 124 |
+
[2025-01-08 18:07:49,114][03286] Decorrelating experience for 0 frames...
|
| 125 |
+
[2025-01-08 18:07:49,112][03285] Decorrelating experience for 0 frames...
|
| 126 |
+
[2025-01-08 18:07:49,120][03281] Decorrelating experience for 0 frames...
|
| 127 |
+
[2025-01-08 18:07:49,123][03282] Decorrelating experience for 0 frames...
|
| 128 |
+
[2025-01-08 18:07:49,940][03279] Decorrelating experience for 0 frames...
|
| 129 |
+
[2025-01-08 18:07:49,953][03280] Decorrelating experience for 0 frames...
|
| 130 |
+
[2025-01-08 18:07:50,246][03286] Decorrelating experience for 32 frames...
|
| 131 |
+
[2025-01-08 18:07:50,249][03285] Decorrelating experience for 32 frames...
|
| 132 |
+
[2025-01-08 18:07:50,255][03282] Decorrelating experience for 32 frames...
|
| 133 |
+
[2025-01-08 18:07:50,606][03280] Decorrelating experience for 32 frames...
|
| 134 |
+
[2025-01-08 18:07:51,417][03284] Decorrelating experience for 32 frames...
|
| 135 |
+
[2025-01-08 18:07:51,525][03279] Decorrelating experience for 32 frames...
|
| 136 |
+
[2025-01-08 18:07:51,821][03281] Decorrelating experience for 32 frames...
|
| 137 |
+
[2025-01-08 18:07:52,248][03282] Decorrelating experience for 64 frames...
|
| 138 |
+
[2025-01-08 18:07:52,250][03286] Decorrelating experience for 64 frames...
|
| 139 |
+
[2025-01-08 18:07:52,257][03285] Decorrelating experience for 64 frames...
|
| 140 |
+
[2025-01-08 18:07:52,267][03280] Decorrelating experience for 64 frames...
|
| 141 |
+
[2025-01-08 18:07:52,764][03283] Decorrelating experience for 64 frames...
|
| 142 |
+
[2025-01-08 18:07:53,022][03284] Decorrelating experience for 64 frames...
|
| 143 |
+
[2025-01-08 18:07:53,477][03281] Decorrelating experience for 64 frames...
|
| 144 |
+
[2025-01-08 18:07:53,514][03280] Decorrelating experience for 96 frames...
|
| 145 |
+
[2025-01-08 18:07:53,589][03282] Decorrelating experience for 96 frames...
|
| 146 |
+
[2025-01-08 18:07:53,601][03285] Decorrelating experience for 96 frames...
|
| 147 |
+
[2025-01-08 18:07:53,820][01481] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 148 |
+
[2025-01-08 18:07:54,218][03283] Decorrelating experience for 96 frames...
|
| 149 |
+
[2025-01-08 18:07:54,237][03286] Decorrelating experience for 96 frames...
|
| 150 |
+
[2025-01-08 18:07:54,324][03284] Decorrelating experience for 96 frames...
|
| 151 |
+
[2025-01-08 18:07:54,727][03279] Decorrelating experience for 64 frames...
|
| 152 |
+
[2025-01-08 18:07:55,294][03281] Decorrelating experience for 96 frames...
|
| 153 |
+
[2025-01-08 18:07:55,521][03279] Decorrelating experience for 96 frames...
|
| 154 |
+
[2025-01-08 18:07:58,823][01481] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 43.6. Samples: 436. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 155 |
+
[2025-01-08 18:07:58,827][01481] Avg episode reward: [(0, '1.692')]
|
| 156 |
+
[2025-01-08 18:07:59,458][03265] Signal inference workers to stop experience collection...
|
| 157 |
+
[2025-01-08 18:07:59,484][03278] InferenceWorker_p0-w0: stopping experience collection
|
| 158 |
+
[2025-01-08 18:08:03,820][01481] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 147.2. Samples: 2208. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 159 |
+
[2025-01-08 18:08:03,823][01481] Avg episode reward: [(0, '2.162')]
|
| 160 |
+
[2025-01-08 18:08:04,613][03265] Signal inference workers to resume experience collection...
|
| 161 |
+
[2025-01-08 18:08:04,614][03278] InferenceWorker_p0-w0: resuming experience collection
|
| 162 |
+
[2025-01-08 18:08:08,820][01481] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 309.8. Samples: 6196. Policy #0 lag: (min: 0.0, avg: 0.2, max: 2.0)
|
| 163 |
+
[2025-01-08 18:08:08,826][01481] Avg episode reward: [(0, '3.603')]
|
| 164 |
+
[2025-01-08 18:08:12,239][03278] Updated weights for policy 0, policy_version 10 (0.0020)
|
| 165 |
+
[2025-01-08 18:08:13,822][01481] Fps is (10 sec: 4505.0, 60 sec: 1802.1, 300 sec: 1802.1). Total num frames: 45056. Throughput: 0: 389.2. Samples: 9730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 166 |
+
[2025-01-08 18:08:13,824][01481] Avg episode reward: [(0, '4.159')]
|
| 167 |
+
[2025-01-08 18:08:18,820][01481] Fps is (10 sec: 3276.8, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 57344. Throughput: 0: 467.7. Samples: 14030. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 168 |
+
[2025-01-08 18:08:18,825][01481] Avg episode reward: [(0, '4.450')]
|
| 169 |
+
[2025-01-08 18:08:23,820][01481] Fps is (10 sec: 3277.2, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 77824. Throughput: 0: 562.3. Samples: 19680. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
|
| 170 |
+
[2025-01-08 18:08:23,822][01481] Avg episode reward: [(0, '4.448')]
|
| 171 |
+
[2025-01-08 18:08:24,316][03278] Updated weights for policy 0, policy_version 20 (0.0027)
|
| 172 |
+
[2025-01-08 18:08:28,820][01481] Fps is (10 sec: 4505.6, 60 sec: 2560.0, 300 sec: 2560.0). Total num frames: 102400. Throughput: 0: 580.9. Samples: 23234. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
| 173 |
+
[2025-01-08 18:08:28,828][01481] Avg episode reward: [(0, '4.265')]
|
| 174 |
+
[2025-01-08 18:08:28,831][03265] Saving new best policy, reward=4.265!
|
| 175 |
+
[2025-01-08 18:08:33,820][01481] Fps is (10 sec: 3686.4, 60 sec: 2548.6, 300 sec: 2548.6). Total num frames: 114688. Throughput: 0: 631.8. Samples: 28432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 176 |
+
[2025-01-08 18:08:33,823][01481] Avg episode reward: [(0, '4.200')]
|
| 177 |
+
[2025-01-08 18:08:37,452][03278] Updated weights for policy 0, policy_version 30 (0.0030)
|
| 178 |
+
[2025-01-08 18:08:38,820][01481] Fps is (10 sec: 2457.6, 60 sec: 2539.5, 300 sec: 2539.5). Total num frames: 126976. Throughput: 0: 716.4. Samples: 32236. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
| 179 |
+
[2025-01-08 18:08:38,827][01481] Avg episode reward: [(0, '4.319')]
|
| 180 |
+
[2025-01-08 18:08:38,831][03265] Saving new best policy, reward=4.319!
|
| 181 |
+
[2025-01-08 18:08:43,820][01481] Fps is (10 sec: 3686.4, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 783.2. Samples: 35678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 182 |
+
[2025-01-08 18:08:43,823][01481] Avg episode reward: [(0, '4.355')]
|
| 183 |
+
[2025-01-08 18:08:43,830][03265] Saving new best policy, reward=4.355!
|
| 184 |
+
[2025-01-08 18:08:46,337][03278] Updated weights for policy 0, policy_version 40 (0.0019)
|
| 185 |
+
[2025-01-08 18:08:48,820][01481] Fps is (10 sec: 4096.0, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 892.7. Samples: 42378. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
| 186 |
+
[2025-01-08 18:08:48,827][01481] Avg episode reward: [(0, '4.407')]
|
| 187 |
+
[2025-01-08 18:08:48,832][03265] Saving new best policy, reward=4.407!
|
| 188 |
+
[2025-01-08 18:08:53,820][01481] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 897.6. Samples: 46588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
| 189 |
+
[2025-01-08 18:08:53,826][01481] Avg episode reward: [(0, '4.432')]
|
| 190 |
+
[2025-01-08 18:08:53,834][03265] Saving new best policy, reward=4.432!
|
| 191 |
+
[2025-01-08 18:08:57,825][03278] Updated weights for policy 0, policy_version 50 (0.0040)
|
| 192 |
+
[2025-01-08 18:08:58,821][01481] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 2984.2). Total num frames: 208896. Throughput: 0: 891.3. Samples: 49838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
| 193 |
+
[2025-01-08 18:08:58,822][01481] Avg episode reward: [(0, '4.377')]
|
| 194 |
+
[2025-01-08 18:09:03,820][01481] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3058.3). Total num frames: 229376. Throughput: 0: 952.1. Samples: 56876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 195 |
+
[2025-01-08 18:09:03,825][01481] Avg episode reward: [(0, '4.433')]
|
| 196 |
+
[2025-01-08 18:09:03,835][03265] Saving new best policy, reward=4.433!
|
| 197 |
+
[2025-01-08 18:09:08,828][01481] Fps is (10 sec: 3274.4, 60 sec: 3617.7, 300 sec: 3020.5). Total num frames: 241664. Throughput: 0: 931.4. Samples: 61600. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 198 |
+
[2025-01-08 18:09:08,830][01481] Avg episode reward: [(0, '4.509')]
|
| 199 |
+
[2025-01-08 18:09:08,880][03278] Updated weights for policy 0, policy_version 60 (0.0022)
|
| 200 |
+
[2025-01-08 18:09:08,886][03265] Saving new best policy, reward=4.509!
|
| 201 |
+
[2025-01-08 18:09:13,820][01481] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 903.9. Samples: 63908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 202 |
+
[2025-01-08 18:09:13,823][01481] Avg episode reward: [(0, '4.460')]
|
| 203 |
+
[2025-01-08 18:09:13,830][03265] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth...
|
| 204 |
+
[2025-01-08 18:09:18,816][03278] Updated weights for policy 0, policy_version 70 (0.0023)
|
| 205 |
+
[2025-01-08 18:09:18,820][01481] Fps is (10 sec: 4509.0, 60 sec: 3822.9, 300 sec: 3185.8). Total num frames: 286720. Throughput: 0: 934.0. Samples: 70464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
| 206 |
+
[2025-01-08 18:09:18,823][01481] Avg episode reward: [(0, '4.261')]
|
| 207 |
+
[2025-01-08 18:09:23,821][01481] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3147.4). Total num frames: 299008. Throughput: 0: 970.3. Samples: 75900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 208 |
+
[2025-01-08 18:09:23,823][01481] Avg episode reward: [(0, '4.314')]
|
| 209 |
+
[2025-01-08 18:09:28,820][01481] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3153.9). Total num frames: 315392. Throughput: 0: 939.6. Samples: 77958. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
| 210 |
+
[2025-01-08 18:09:28,827][01481] Avg episode reward: [(0, '4.418')]
|
| 211 |
+
[2025-01-08 18:09:30,916][03278] Updated weights for policy 0, policy_version 80 (0.0017)
|
| 212 |
+
[2025-01-08 18:09:33,820][01481] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3237.8). Total num frames: 339968. Throughput: 0: 926.2. Samples: 84058. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
| 213 |
+
[2025-01-08 18:09:33,828][01481] Avg episode reward: [(0, '4.295')]
|
| 214 |
+
[2025-01-08 18:09:38,820][01481] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3276.8). Total num frames: 360448. Throughput: 0: 973.0. Samples: 90374. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 215 |
+
[2025-01-08 18:09:38,828][01481] Avg episode reward: [(0, '4.214')]
|
| 216 |
+
[2025-01-08 18:09:42,629][03278] Updated weights for policy 0, policy_version 90 (0.0018)
|
| 217 |
+
[2025-01-08 18:09:43,826][01481] Fps is (10 sec: 2865.6, 60 sec: 3617.8, 300 sec: 3205.4). Total num frames: 368640. Throughput: 0: 936.8. Samples: 92000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 218 |
+
[2025-01-08 18:09:43,830][01481] Avg episode reward: [(0, '4.260')]
|
| 219 |
+
[2025-01-08 18:09:48,820][01481] Fps is (10 sec: 2048.0, 60 sec: 3549.9, 300 sec: 3174.4). Total num frames: 380928. Throughput: 0: 852.0. Samples: 95218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 220 |
+
[2025-01-08 18:09:48,823][01481] Avg episode reward: [(0, '4.373')]
|
| 221 |
+
[2025-01-08 18:09:53,820][01481] Fps is (10 sec: 3278.6, 60 sec: 3618.1, 300 sec: 3211.3). Total num frames: 401408. Throughput: 0: 874.3. Samples: 100938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 222 |
+
[2025-01-08 18:09:53,824][01481] Avg episode reward: [(0, '4.383')]
|
| 223 |
+
[2025-01-08 18:09:55,221][03278] Updated weights for policy 0, policy_version 100 (0.0033)
|
| 224 |
+
[2025-01-08 18:09:58,823][01481] Fps is (10 sec: 4504.4, 60 sec: 3618.0, 300 sec: 3276.7). Total num frames: 425984. Throughput: 0: 899.1. Samples: 104370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 225 |
+
[2025-01-08 18:09:58,826][01481] Avg episode reward: [(0, '4.462')]
|
| 226 |
+
[2025-01-08 18:09:59,546][01481] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 1481], exiting...
|
| 227 |
+
[2025-01-08 18:09:59,556][03265] Stopping Batcher_0...
|
| 228 |
+
[2025-01-08 18:09:59,558][03265] Loop batcher_evt_loop terminating...
|
| 229 |
+
[2025-01-08 18:09:59,556][01481] Runner profile tree view:
|
| 230 |
+
main_loop: 159.8596
|
| 231 |
+
[2025-01-08 18:09:59,562][01481] Collected {0: 425984}, FPS: 2664.7
|
| 232 |
+
[2025-01-08 18:09:59,563][03265] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000104_425984.pth...
|
| 233 |
+
[2025-01-08 18:09:59,740][03278] Weights refcount: 2 0
|
| 234 |
+
[2025-01-08 18:09:59,749][03278] Stopping InferenceWorker_p0-w0...
|
| 235 |
+
[2025-01-08 18:09:59,750][03278] Loop inference_proc0-0_evt_loop terminating...
|
| 236 |
+
[2025-01-08 18:09:59,886][03280] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance0'), args=(1, 0)
|
| 237 |
+
Traceback (most recent call last):
|
| 238 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 239 |
+
slot_callable(*args)
|
| 240 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 241 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 242 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 243 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 244 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 245 |
+
return self.env.step(action)
|
| 246 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 247 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 248 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 249 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 250 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 251 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 252 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 253 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 254 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 255 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 256 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 257 |
+
return self.env.step(action)
|
| 258 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 259 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 260 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 261 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 262 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 263 |
+
[2025-01-08 18:09:59,941][03280] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc0_evt_loop
|
| 264 |
+
[2025-01-08 18:09:59,930][03265] Stopping LearnerWorker_p0...
|
| 265 |
+
[2025-01-08 18:09:59,942][03265] Loop learner_proc0_evt_loop terminating...
|
| 266 |
+
[2025-01-08 18:09:59,955][03283] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance4'), args=(0, 0)
|
| 267 |
+
Traceback (most recent call last):
|
| 268 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 269 |
+
slot_callable(*args)
|
| 270 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 271 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 272 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 273 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 274 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 275 |
+
return self.env.step(action)
|
| 276 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 277 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 278 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 279 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 280 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 281 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 282 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 283 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 284 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 285 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 286 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 287 |
+
return self.env.step(action)
|
| 288 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 289 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 290 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 291 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 292 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 293 |
+
[2025-01-08 18:09:59,961][03283] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc4_evt_loop
|
| 294 |
+
[2025-01-08 18:10:00,088][03279] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance2'), args=(1, 0)
|
| 295 |
+
Traceback (most recent call last):
|
| 296 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 297 |
+
slot_callable(*args)
|
| 298 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 299 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 300 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 301 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 302 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 303 |
+
return self.env.step(action)
|
| 304 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 305 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 306 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 307 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 308 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 309 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 310 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 311 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 312 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 313 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 314 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 315 |
+
return self.env.step(action)
|
| 316 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 317 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 318 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 319 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 320 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 321 |
+
[2025-01-08 18:10:00,090][03279] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc2_evt_loop
|
| 322 |
+
[2025-01-08 18:10:00,056][03284] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance6'), args=(1, 0)
|
| 323 |
+
Traceback (most recent call last):
|
| 324 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 325 |
+
slot_callable(*args)
|
| 326 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 327 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 328 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 329 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 330 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 331 |
+
return self.env.step(action)
|
| 332 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 333 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 334 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 335 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 336 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 337 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 338 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 339 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 340 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 341 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 342 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 343 |
+
return self.env.step(action)
|
| 344 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 345 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 346 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 347 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 348 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 349 |
+
[2025-01-08 18:10:00,093][03284] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc6_evt_loop
|
| 350 |
+
[2025-01-08 18:10:00,055][03285] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance5'), args=(0, 0)
|
| 351 |
+
Traceback (most recent call last):
|
| 352 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 353 |
+
slot_callable(*args)
|
| 354 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 355 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 356 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 357 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 358 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 359 |
+
return self.env.step(action)
|
| 360 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 361 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 362 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 363 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 364 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 365 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 366 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 367 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 368 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 369 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 370 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 371 |
+
return self.env.step(action)
|
| 372 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 373 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 374 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 375 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 376 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 377 |
+
[2025-01-08 18:10:00,152][03285] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop
|
| 378 |
+
[2025-01-08 18:10:00,139][03286] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance7'), args=(0, 0)
|
| 379 |
+
Traceback (most recent call last):
|
| 380 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 381 |
+
slot_callable(*args)
|
| 382 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 383 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 384 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 385 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 386 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 387 |
+
return self.env.step(action)
|
| 388 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 389 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 390 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 391 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 392 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 393 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 394 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 395 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 396 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 397 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 398 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 399 |
+
return self.env.step(action)
|
| 400 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 401 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 402 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 403 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 404 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 405 |
+
[2025-01-08 18:10:00,194][03286] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc7_evt_loop
|
| 406 |
+
[2025-01-08 18:10:00,212][03282] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance1'), args=(0, 0)
|
| 407 |
+
Traceback (most recent call last):
|
| 408 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 409 |
+
slot_callable(*args)
|
| 410 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 411 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 412 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 413 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 414 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 415 |
+
return self.env.step(action)
|
| 416 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 417 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 418 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 419 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 420 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 421 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 422 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 423 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 424 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 425 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 426 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 427 |
+
return self.env.step(action)
|
| 428 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 429 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 430 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 431 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 432 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 433 |
+
[2025-01-08 18:10:00,250][03282] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc1_evt_loop
|
| 434 |
+
[2025-01-08 18:10:00,344][03281] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance3'), args=(1, 0)
|
| 435 |
+
Traceback (most recent call last):
|
| 436 |
+
File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
| 437 |
+
slot_callable(*args)
|
| 438 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts
|
| 439 |
+
complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing)
|
| 440 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts
|
| 441 |
+
new_obs, rewards, terminated, truncated, infos = e.step(actions)
|
| 442 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 443 |
+
return self.env.step(action)
|
| 444 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step
|
| 445 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 446 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step
|
| 447 |
+
obs, rew, terminated, truncated, info = self.env.step(action)
|
| 448 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step
|
| 449 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 450 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step
|
| 451 |
+
observation, reward, terminated, truncated, info = self.env.step(action)
|
| 452 |
+
File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step
|
| 453 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 454 |
+
File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step
|
| 455 |
+
return self.env.step(action)
|
| 456 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step
|
| 457 |
+
obs, reward, terminated, truncated, info = self.env.step(action)
|
| 458 |
+
File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step
|
| 459 |
+
reward = self.game.make_action(actions_flattened, self.skip_frames)
|
| 460 |
+
vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed.
|
| 461 |
+
[2025-01-08 18:10:00,359][03281] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc3_evt_loop
|
| 462 |
+
[2025-01-08 18:10:01,515][01481] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
| 463 |
+
[2025-01-08 18:10:01,522][01481] Overriding arg 'num_workers' with value 1 passed from command line
|
| 464 |
+
[2025-01-08 18:10:01,528][01481] Adding new argument 'no_render'=True that is not in the saved config file!
|
| 465 |
+
[2025-01-08 18:10:01,530][01481] Adding new argument 'save_video'=True that is not in the saved config file!
|
| 466 |
+
[2025-01-08 18:10:01,533][01481] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
| 467 |
+
[2025-01-08 18:10:01,535][01481] Adding new argument 'video_name'=None that is not in the saved config file!
|
| 468 |
+
[2025-01-08 18:10:01,552][01481] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
| 469 |
+
[2025-01-08 18:10:01,557][01481] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
| 470 |
+
[2025-01-08 18:10:01,562][01481] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
| 471 |
+
[2025-01-08 18:10:01,581][01481] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
| 472 |
+
[2025-01-08 18:10:01,583][01481] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
| 473 |
+
[2025-01-08 18:10:01,586][01481] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
| 474 |
+
[2025-01-08 18:10:01,601][01481] Adding new argument 'train_script'=None that is not in the saved config file!
|
| 475 |
+
[2025-01-08 18:10:01,604][01481] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
| 476 |
+
[2025-01-08 18:10:01,657][01481] Using frameskip 1 and render_action_repeat=4 for evaluation
|
| 477 |
+
[2025-01-08 18:10:01,747][01481] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 478 |
+
[2025-01-08 18:10:01,752][01481] RunningMeanStd input shape: (3, 72, 128)
|
| 479 |
+
[2025-01-08 18:10:01,761][01481] RunningMeanStd input shape: (1,)
|
| 480 |
+
[2025-01-08 18:10:01,796][01481] ConvEncoder: input_channels=3
|
| 481 |
+
[2025-01-08 18:10:02,139][01481] Conv encoder output size: 512
|
| 482 |
+
[2025-01-08 18:10:02,143][01481] Policy head output size: 512
|
| 483 |
+
[2025-01-08 18:10:02,663][01481] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000104_425984.pth...
|
| 484 |
+
[2025-01-08 18:10:05,006][01481] Num frames 100...
|
| 485 |
+
[2025-01-08 18:10:05,235][01481] Num frames 200...
|
| 486 |
+
[2025-01-08 18:10:05,435][01481] Num frames 300...
|
| 487 |
+
[2025-01-08 18:10:05,662][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
| 488 |
+
[2025-01-08 18:10:05,664][01481] Avg episode reward: 3.840, avg true_objective: 3.840
|
| 489 |
+
[2025-01-08 18:10:05,701][01481] Num frames 400...
|
| 490 |
+
[2025-01-08 18:10:05,914][01481] Num frames 500...
|
| 491 |
+
[2025-01-08 18:10:06,147][01481] Num frames 600...
|
| 492 |
+
[2025-01-08 18:10:06,346][01481] Num frames 700...
|
| 493 |
+
[2025-01-08 18:10:06,545][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
| 494 |
+
[2025-01-08 18:10:06,551][01481] Avg episode reward: 3.840, avg true_objective: 3.840
|
| 495 |
+
[2025-01-08 18:10:06,619][01481] Num frames 800...
|
| 496 |
+
[2025-01-08 18:10:06,819][01481] Num frames 900...
|
| 497 |
+
[2025-01-08 18:10:07,029][01481] Num frames 1000...
|
| 498 |
+
[2025-01-08 18:10:07,225][01481] Num frames 1100...
|
| 499 |
+
[2025-01-08 18:10:07,371][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
| 500 |
+
[2025-01-08 18:10:07,373][01481] Avg episode reward: 3.840, avg true_objective: 3.840
|
| 501 |
+
[2025-01-08 18:11:05,889][01481] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
|
| 502 |
+
[2025-01-08 18:11:05,891][01481] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
|
| 503 |
+
[2025-01-08 18:11:05,893][01481] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
|
| 504 |
+
[2025-01-08 18:11:05,895][01481] Overriding arg 'train_dir' with value 'train_dir' passed from command line
|
| 505 |
+
[2025-01-08 18:11:05,896][01481] Overriding arg 'num_workers' with value 1 passed from command line
|
| 506 |
+
[2025-01-08 18:11:05,898][01481] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
|
| 507 |
+
[2025-01-08 18:11:05,900][01481] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
|
| 508 |
+
[2025-01-08 18:11:05,900][01481] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
|
| 509 |
+
[2025-01-08 18:11:05,901][01481] Adding new argument 'no_render'=True that is not in the saved config file!
|
| 510 |
+
[2025-01-08 18:11:05,902][01481] Adding new argument 'save_video'=True that is not in the saved config file!
|
| 511 |
+
[2025-01-08 18:11:05,903][01481] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
| 512 |
+
[2025-01-08 18:11:05,904][01481] Adding new argument 'video_name'=None that is not in the saved config file!
|
| 513 |
+
[2025-01-08 18:11:05,905][01481] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
| 514 |
+
[2025-01-08 18:11:05,906][01481] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
| 515 |
+
[2025-01-08 18:11:05,907][01481] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
| 516 |
+
[2025-01-08 18:11:05,908][01481] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
| 517 |
+
[2025-01-08 18:11:05,909][01481] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
| 518 |
+
[2025-01-08 18:11:05,910][01481] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
| 519 |
+
[2025-01-08 18:11:05,911][01481] Adding new argument 'train_script'=None that is not in the saved config file!
|
| 520 |
+
[2025-01-08 18:11:05,912][01481] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
| 521 |
+
[2025-01-08 18:11:05,913][01481] Using frameskip 1 and render_action_repeat=4 for evaluation
|
| 522 |
+
[2025-01-08 18:11:05,953][01481] RunningMeanStd input shape: (3, 72, 128)
|
| 523 |
+
[2025-01-08 18:11:05,954][01481] RunningMeanStd input shape: (1,)
|
| 524 |
+
[2025-01-08 18:11:05,970][01481] ConvEncoder: input_channels=3
|
| 525 |
+
[2025-01-08 18:11:06,018][01481] Conv encoder output size: 512
|
| 526 |
+
[2025-01-08 18:11:06,020][01481] Policy head output size: 512
|
| 527 |
+
[2025-01-08 18:11:06,043][01481] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
|
| 528 |
+
[2025-01-08 18:11:06,482][01481] Num frames 100...
|
| 529 |
+
[2025-01-08 18:11:06,616][01481] Num frames 200...
|
| 530 |
+
[2025-01-08 18:11:06,738][01481] Num frames 300...
|
| 531 |
+
[2025-01-08 18:11:06,865][01481] Num frames 400...
|
| 532 |
+
[2025-01-08 18:11:06,990][01481] Num frames 500...
|
| 533 |
+
[2025-01-08 18:11:07,114][01481] Num frames 600...
|
| 534 |
+
[2025-01-08 18:11:07,243][01481] Num frames 700...
|
| 535 |
+
[2025-01-08 18:11:07,372][01481] Num frames 800...
|
| 536 |
+
[2025-01-08 18:11:07,498][01481] Num frames 900...
|
| 537 |
+
[2025-01-08 18:11:07,629][01481] Num frames 1000...
|
| 538 |
+
[2025-01-08 18:11:07,755][01481] Num frames 1100...
|
| 539 |
+
[2025-01-08 18:11:07,883][01481] Num frames 1200...
|
| 540 |
+
[2025-01-08 18:11:08,010][01481] Num frames 1300...
|
| 541 |
+
[2025-01-08 18:11:08,142][01481] Num frames 1400...
|
| 542 |
+
[2025-01-08 18:11:08,272][01481] Num frames 1500...
|
| 543 |
+
[2025-01-08 18:11:08,405][01481] Num frames 1600...
|
| 544 |
+
[2025-01-08 18:11:08,530][01481] Num frames 1700...
|
| 545 |
+
[2025-01-08 18:11:08,661][01481] Num frames 1800...
|
| 546 |
+
[2025-01-08 18:11:08,786][01481] Num frames 1900...
|
| 547 |
+
[2025-01-08 18:11:08,920][01481] Num frames 2000...
|
| 548 |
+
[2025-01-08 18:11:09,046][01481] Num frames 2100...
|
| 549 |
+
[2025-01-08 18:11:09,098][01481] Avg episode rewards: #0: 55.999, true rewards: #0: 21.000
|
| 550 |
+
[2025-01-08 18:11:09,100][01481] Avg episode reward: 55.999, avg true_objective: 21.000
|
| 551 |
+
[2025-01-08 18:11:09,229][01481] Num frames 2200...
|
| 552 |
+
[2025-01-08 18:11:09,359][01481] Num frames 2300...
|
| 553 |
+
[2025-01-08 18:11:09,481][01481] Num frames 2400...
|
| 554 |
+
[2025-01-08 18:11:09,604][01481] Num frames 2500...
|
| 555 |
+
[2025-01-08 18:11:09,735][01481] Num frames 2600...
|
| 556 |
+
[2025-01-08 18:11:09,859][01481] Num frames 2700...
|
| 557 |
+
[2025-01-08 18:11:09,984][01481] Num frames 2800...
|
| 558 |
+
[2025-01-08 18:11:10,105][01481] Num frames 2900...
|
| 559 |
+
[2025-01-08 18:11:10,233][01481] Num frames 3000...
|
| 560 |
+
[2025-01-08 18:11:10,361][01481] Num frames 3100...
|
| 561 |
+
[2025-01-08 18:11:10,484][01481] Num frames 3200...
|
| 562 |
+
[2025-01-08 18:11:10,607][01481] Num frames 3300...
|
| 563 |
+
[2025-01-08 18:11:10,737][01481] Num frames 3400...
|
| 564 |
+
[2025-01-08 18:11:10,869][01481] Num frames 3500...
|
| 565 |
+
[2025-01-08 18:11:10,999][01481] Num frames 3600...
|
| 566 |
+
[2025-01-08 18:11:11,123][01481] Num frames 3700...
|
| 567 |
+
[2025-01-08 18:11:11,251][01481] Num frames 3800...
|
| 568 |
+
[2025-01-08 18:11:11,388][01481] Num frames 3900...
|
| 569 |
+
[2025-01-08 18:11:11,517][01481] Num frames 4000...
|
| 570 |
+
[2025-01-08 18:11:11,639][01481] Num frames 4100...
|
| 571 |
+
[2025-01-08 18:11:11,774][01481] Num frames 4200...
|
| 572 |
+
[2025-01-08 18:11:11,826][01481] Avg episode rewards: #0: 61.999, true rewards: #0: 21.000
|
| 573 |
+
[2025-01-08 18:11:11,828][01481] Avg episode reward: 61.999, avg true_objective: 21.000
|
| 574 |
+
[2025-01-08 18:11:11,954][01481] Num frames 4300...
|
| 575 |
+
[2025-01-08 18:11:12,081][01481] Num frames 4400...
|
| 576 |
+
[2025-01-08 18:11:12,204][01481] Num frames 4500...
|
| 577 |
+
[2025-01-08 18:11:12,332][01481] Num frames 4600...
|
| 578 |
+
[2025-01-08 18:11:12,460][01481] Num frames 4700...
|
| 579 |
+
[2025-01-08 18:11:12,590][01481] Num frames 4800...
|
| 580 |
+
[2025-01-08 18:11:12,725][01481] Num frames 4900...
|
| 581 |
+
[2025-01-08 18:11:12,862][01481] Num frames 5000...
|
| 582 |
+
[2025-01-08 18:11:12,986][01481] Num frames 5100...
|
| 583 |
+
[2025-01-08 18:11:13,110][01481] Num frames 5200...
|
| 584 |
+
[2025-01-08 18:11:13,236][01481] Num frames 5300...
|
| 585 |
+
[2025-01-08 18:11:13,364][01481] Num frames 5400...
|
| 586 |
+
[2025-01-08 18:11:13,494][01481] Num frames 5500...
|
| 587 |
+
[2025-01-08 18:11:13,615][01481] Num frames 5600...
|
| 588 |
+
[2025-01-08 18:11:13,743][01481] Num frames 5700...
|
| 589 |
+
[2025-01-08 18:11:13,876][01481] Num frames 5800...
|
| 590 |
+
[2025-01-08 18:11:14,002][01481] Num frames 5900...
|
| 591 |
+
[2025-01-08 18:11:14,126][01481] Num frames 6000...
|
| 592 |
+
[2025-01-08 18:11:14,250][01481] Num frames 6100...
|
| 593 |
+
[2025-01-08 18:11:14,380][01481] Num frames 6200...
|
| 594 |
+
[2025-01-08 18:11:14,507][01481] Num frames 6300...
|
| 595 |
+
[2025-01-08 18:11:14,560][01481] Avg episode rewards: #0: 64.666, true rewards: #0: 21.000
|
| 596 |
+
[2025-01-08 18:11:14,562][01481] Avg episode reward: 64.666, avg true_objective: 21.000
|
| 597 |
+
[2025-01-08 18:11:14,739][01481] Num frames 6400...
|
| 598 |
+
[2025-01-08 18:11:14,924][01481] Num frames 6500...
|
| 599 |
+
[2025-01-08 18:11:15,091][01481] Num frames 6600...
|
| 600 |
+
[2025-01-08 18:11:15,262][01481] Num frames 6700...
|
| 601 |
+
[2025-01-08 18:11:15,438][01481] Num frames 6800...
|
| 602 |
+
[2025-01-08 18:11:15,607][01481] Num frames 6900...
|
| 603 |
+
[2025-01-08 18:11:15,771][01481] Num frames 7000...
|
| 604 |
+
[2025-01-08 18:11:15,961][01481] Num frames 7100...
|
| 605 |
+
[2025-01-08 18:11:16,147][01481] Num frames 7200...
|
| 606 |
+
[2025-01-08 18:11:16,322][01481] Num frames 7300...
|
| 607 |
+
[2025-01-08 18:11:16,517][01481] Num frames 7400...
|
| 608 |
+
[2025-01-08 18:11:16,694][01481] Num frames 7500...
|
| 609 |
+
[2025-01-08 18:11:16,871][01481] Num frames 7600...
|
| 610 |
+
[2025-01-08 18:11:17,065][01481] Num frames 7700...
|
| 611 |
+
[2025-01-08 18:11:17,228][01481] Num frames 7800...
|
| 612 |
+
[2025-01-08 18:11:17,361][01481] Num frames 7900...
|
| 613 |
+
[2025-01-08 18:11:17,487][01481] Num frames 8000...
|
| 614 |
+
[2025-01-08 18:11:17,609][01481] Num frames 8100...
|
| 615 |
+
[2025-01-08 18:11:17,733][01481] Num frames 8200...
|
| 616 |
+
[2025-01-08 18:11:17,862][01481] Num frames 8300...
|
| 617 |
+
[2025-01-08 18:11:18,007][01481] Num frames 8400...
|
| 618 |
+
[2025-01-08 18:11:18,060][01481] Avg episode rewards: #0: 64.499, true rewards: #0: 21.000
|
| 619 |
+
[2025-01-08 18:11:18,062][01481] Avg episode reward: 64.499, avg true_objective: 21.000
|
| 620 |
+
[2025-01-08 18:11:18,192][01481] Num frames 8500...
|
| 621 |
+
[2025-01-08 18:11:18,323][01481] Num frames 8600...
|
| 622 |
+
[2025-01-08 18:11:18,461][01481] Num frames 8700...
|
| 623 |
+
[2025-01-08 18:11:18,589][01481] Num frames 8800...
|
| 624 |
+
[2025-01-08 18:11:18,718][01481] Num frames 8900...
|
| 625 |
+
[2025-01-08 18:11:18,846][01481] Num frames 9000...
|
| 626 |
+
[2025-01-08 18:11:18,971][01481] Num frames 9100...
|
| 627 |
+
[2025-01-08 18:11:19,108][01481] Num frames 9200...
|
| 628 |
+
[2025-01-08 18:11:19,236][01481] Num frames 9300...
|
| 629 |
+
[2025-01-08 18:11:19,368][01481] Num frames 9400...
|
| 630 |
+
[2025-01-08 18:11:19,491][01481] Num frames 9500...
|
| 631 |
+
[2025-01-08 18:11:19,614][01481] Num frames 9600...
|
| 632 |
+
[2025-01-08 18:11:19,737][01481] Num frames 9700...
|
| 633 |
+
[2025-01-08 18:11:19,861][01481] Num frames 9800...
|
| 634 |
+
[2025-01-08 18:11:19,989][01481] Num frames 9900...
|
| 635 |
+
[2025-01-08 18:11:20,123][01481] Num frames 10000...
|
| 636 |
+
[2025-01-08 18:11:20,250][01481] Num frames 10100...
|
| 637 |
+
[2025-01-08 18:11:20,387][01481] Num frames 10200...
|
| 638 |
+
[2025-01-08 18:11:20,517][01481] Num frames 10300...
|
| 639 |
+
[2025-01-08 18:11:20,643][01481] Num frames 10400...
|
| 640 |
+
[2025-01-08 18:11:20,789][01481] Num frames 10500...
|
| 641 |
+
[2025-01-08 18:11:20,843][01481] Avg episode rewards: #0: 63.999, true rewards: #0: 21.000
|
| 642 |
+
[2025-01-08 18:11:20,845][01481] Avg episode reward: 63.999, avg true_objective: 21.000
|
| 643 |
+
[2025-01-08 18:11:20,976][01481] Num frames 10600...
|
| 644 |
+
[2025-01-08 18:11:21,109][01481] Num frames 10700...
|
| 645 |
+
[2025-01-08 18:11:21,236][01481] Num frames 10800...
|
| 646 |
+
[2025-01-08 18:11:21,365][01481] Num frames 10900...
|
| 647 |
+
[2025-01-08 18:11:21,490][01481] Num frames 11000...
|
| 648 |
+
[2025-01-08 18:11:21,611][01481] Num frames 11100...
|
| 649 |
+
[2025-01-08 18:11:21,733][01481] Num frames 11200...
|
| 650 |
+
[2025-01-08 18:11:21,858][01481] Num frames 11300...
|
| 651 |
+
[2025-01-08 18:11:21,984][01481] Num frames 11400...
|
| 652 |
+
[2025-01-08 18:11:22,121][01481] Num frames 11500...
|
| 653 |
+
[2025-01-08 18:11:22,248][01481] Num frames 11600...
|
| 654 |
+
[2025-01-08 18:11:22,384][01481] Num frames 11700...
|
| 655 |
+
[2025-01-08 18:11:22,509][01481] Num frames 11800...
|
| 656 |
+
[2025-01-08 18:11:22,634][01481] Num frames 11900...
|
| 657 |
+
[2025-01-08 18:11:22,759][01481] Num frames 12000...
|
| 658 |
+
[2025-01-08 18:11:22,884][01481] Num frames 12100...
|
| 659 |
+
[2025-01-08 18:11:23,012][01481] Num frames 12200...
|
| 660 |
+
[2025-01-08 18:11:23,144][01481] Num frames 12300...
|
| 661 |
+
[2025-01-08 18:11:23,279][01481] Num frames 12400...
|
| 662 |
+
[2025-01-08 18:11:23,402][01481] Num frames 12500...
|
| 663 |
+
[2025-01-08 18:11:23,528][01481] Num frames 12600...
|
| 664 |
+
[2025-01-08 18:11:23,581][01481] Avg episode rewards: #0: 63.499, true rewards: #0: 21.000
|
| 665 |
+
[2025-01-08 18:11:23,582][01481] Avg episode reward: 63.499, avg true_objective: 21.000
|
| 666 |
+
[2025-01-08 18:11:23,706][01481] Num frames 12700...
|
| 667 |
+
[2025-01-08 18:11:23,831][01481] Num frames 12800...
|
| 668 |
+
[2025-01-08 18:11:23,960][01481] Num frames 12900...
|
| 669 |
+
[2025-01-08 18:11:24,089][01481] Num frames 13000...
|
| 670 |
+
[2025-01-08 18:11:24,224][01481] Num frames 13100...
|
| 671 |
+
[2025-01-08 18:11:24,356][01481] Num frames 13200...
|
| 672 |
+
[2025-01-08 18:11:24,481][01481] Num frames 13300...
|
| 673 |
+
[2025-01-08 18:11:24,605][01481] Num frames 13400...
|
| 674 |
+
[2025-01-08 18:11:24,728][01481] Num frames 13500...
|
| 675 |
+
[2025-01-08 18:11:24,860][01481] Num frames 13600...
|
| 676 |
+
[2025-01-08 18:11:24,985][01481] Num frames 13700...
|
| 677 |
+
[2025-01-08 18:11:25,110][01481] Num frames 13800...
|
| 678 |
+
[2025-01-08 18:11:25,244][01481] Num frames 13900...
|
| 679 |
+
[2025-01-08 18:11:25,318][01481] Avg episode rewards: #0: 59.445, true rewards: #0: 19.874
|
| 680 |
+
[2025-01-08 18:11:25,320][01481] Avg episode reward: 59.445, avg true_objective: 19.874
|
| 681 |
+
[2025-01-08 18:11:25,428][01481] Num frames 14000...
|
| 682 |
+
[2025-01-08 18:11:25,551][01481] Num frames 14100...
|
| 683 |
+
[2025-01-08 18:11:25,677][01481] Num frames 14200...
|
| 684 |
+
[2025-01-08 18:11:25,802][01481] Num frames 14300...
|
| 685 |
+
[2025-01-08 18:11:25,929][01481] Num frames 14400...
|
| 686 |
+
[2025-01-08 18:11:26,058][01481] Num frames 14500...
|
| 687 |
+
[2025-01-08 18:11:26,191][01481] Num frames 14600...
|
| 688 |
+
[2025-01-08 18:11:26,324][01481] Num frames 14700...
|
| 689 |
+
[2025-01-08 18:11:26,448][01481] Num frames 14800...
|
| 690 |
+
[2025-01-08 18:11:26,573][01481] Num frames 14900...
|
| 691 |
+
[2025-01-08 18:11:26,695][01481] Num frames 15000...
|
| 692 |
+
[2025-01-08 18:11:26,830][01481] Num frames 15100...
|
| 693 |
+
[2025-01-08 18:11:26,959][01481] Num frames 15200...
|
| 694 |
+
[2025-01-08 18:11:27,087][01481] Num frames 15300...
|
| 695 |
+
[2025-01-08 18:11:27,261][01481] Num frames 15400...
|
| 696 |
+
[2025-01-08 18:11:27,449][01481] Num frames 15500...
|
| 697 |
+
[2025-01-08 18:11:27,621][01481] Num frames 15600...
|
| 698 |
+
[2025-01-08 18:11:27,791][01481] Num frames 15700...
|
| 699 |
+
[2025-01-08 18:11:27,969][01481] Num frames 15800...
|
| 700 |
+
[2025-01-08 18:11:28,139][01481] Num frames 15900...
|
| 701 |
+
[2025-01-08 18:11:28,323][01481] Num frames 16000...
|
| 702 |
+
[2025-01-08 18:11:28,401][01481] Avg episode rewards: #0: 59.889, true rewards: #0: 20.015
|
| 703 |
+
[2025-01-08 18:11:28,403][01481] Avg episode reward: 59.889, avg true_objective: 20.015
|
| 704 |
+
[2025-01-08 18:11:28,552][01481] Num frames 16100...
|
| 705 |
+
[2025-01-08 18:11:28,737][01481] Num frames 16200...
|
| 706 |
+
[2025-01-08 18:11:28,912][01481] Num frames 16300...
|
| 707 |
+
[2025-01-08 18:11:29,095][01481] Num frames 16400...
|
| 708 |
+
[2025-01-08 18:11:29,277][01481] Num frames 16500...
|
| 709 |
+
[2025-01-08 18:11:29,460][01481] Num frames 16600...
|
| 710 |
+
[2025-01-08 18:11:29,636][01481] Num frames 16700...
|
| 711 |
+
[2025-01-08 18:11:29,809][01481] Num frames 16800...
|
| 712 |
+
[2025-01-08 18:11:29,933][01481] Num frames 16900...
|
| 713 |
+
[2025-01-08 18:11:30,056][01481] Num frames 17000...
|
| 714 |
+
[2025-01-08 18:11:30,187][01481] Num frames 17100...
|
| 715 |
+
[2025-01-08 18:11:30,317][01481] Num frames 17200...
|
| 716 |
+
[2025-01-08 18:11:30,454][01481] Num frames 17300...
|
| 717 |
+
[2025-01-08 18:11:30,579][01481] Num frames 17400...
|
| 718 |
+
[2025-01-08 18:11:30,704][01481] Num frames 17500...
|
| 719 |
+
[2025-01-08 18:11:30,833][01481] Num frames 17600...
|
| 720 |
+
[2025-01-08 18:11:30,949][01481] Avg episode rewards: #0: 58.497, true rewards: #0: 19.609
|
| 721 |
+
[2025-01-08 18:11:30,951][01481] Avg episode reward: 58.497, avg true_objective: 19.609
|
| 722 |
+
[2025-01-08 18:11:31,021][01481] Num frames 17700...
|
| 723 |
+
[2025-01-08 18:11:31,143][01481] Num frames 17800...
|
| 724 |
+
[2025-01-08 18:11:31,276][01481] Num frames 17900...
|
| 725 |
+
[2025-01-08 18:11:31,414][01481] Num frames 18000...
|
| 726 |
+
[2025-01-08 18:11:31,539][01481] Num frames 18100...
|
| 727 |
+
[2025-01-08 18:11:31,665][01481] Num frames 18200...
|
| 728 |
+
[2025-01-08 18:11:31,791][01481] Num frames 18300...
|
| 729 |
+
[2025-01-08 18:11:31,917][01481] Num frames 18400...
|
| 730 |
+
[2025-01-08 18:11:32,045][01481] Num frames 18500...
|
| 731 |
+
[2025-01-08 18:11:32,172][01481] Num frames 18600...
|
| 732 |
+
[2025-01-08 18:11:32,309][01481] Num frames 18700...
|
| 733 |
+
[2025-01-08 18:11:32,445][01481] Num frames 18800...
|
| 734 |
+
[2025-01-08 18:11:32,573][01481] Num frames 18900...
|
| 735 |
+
[2025-01-08 18:11:32,700][01481] Num frames 19000...
|
| 736 |
+
[2025-01-08 18:11:32,826][01481] Num frames 19100...
|
| 737 |
+
[2025-01-08 18:11:32,958][01481] Num frames 19200...
|
| 738 |
+
[2025-01-08 18:11:33,084][01481] Num frames 19300...
|
| 739 |
+
[2025-01-08 18:11:33,214][01481] Num frames 19400...
|
| 740 |
+
[2025-01-08 18:11:33,350][01481] Num frames 19500...
|
| 741 |
+
[2025-01-08 18:11:33,486][01481] Num frames 19600...
|
| 742 |
+
[2025-01-08 18:11:33,658][01481] Num frames 19700...
|
| 743 |
+
[2025-01-08 18:11:33,815][01481] Avg episode rewards: #0: 59.047, true rewards: #0: 19.748
|
| 744 |
+
[2025-01-08 18:11:33,817][01481] Avg episode reward: 59.047, avg true_objective: 19.748
|
| 745 |
+
[2025-01-08 18:13:39,180][01481] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
|
| 746 |
+
[2025-01-08 18:15:38,880][01481] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
|
| 747 |
+
[2025-01-08 18:15:38,882][01481] Overriding arg 'num_workers' with value 1 passed from command line
|
| 748 |
+
[2025-01-08 18:15:38,883][01481] Adding new argument 'no_render'=True that is not in the saved config file!
|
| 749 |
+
[2025-01-08 18:15:38,885][01481] Adding new argument 'save_video'=True that is not in the saved config file!
|
| 750 |
+
[2025-01-08 18:15:38,887][01481] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
| 751 |
+
[2025-01-08 18:15:38,889][01481] Adding new argument 'video_name'=None that is not in the saved config file!
|
| 752 |
+
[2025-01-08 18:15:38,890][01481] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
| 753 |
+
[2025-01-08 18:15:38,892][01481] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
| 754 |
+
[2025-01-08 18:15:38,893][01481] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
| 755 |
+
[2025-01-08 18:15:38,894][01481] Adding new argument 'hf_repository'='jdollman/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
| 756 |
+
[2025-01-08 18:15:38,895][01481] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
| 757 |
+
[2025-01-08 18:15:38,896][01481] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
| 758 |
+
[2025-01-08 18:15:38,897][01481] Adding new argument 'train_script'=None that is not in the saved config file!
|
| 759 |
+
[2025-01-08 18:15:38,898][01481] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
| 760 |
+
[2025-01-08 18:15:38,899][01481] Using frameskip 1 and render_action_repeat=4 for evaluation
|
| 761 |
+
[2025-01-08 18:15:38,928][01481] RunningMeanStd input shape: (3, 72, 128)
|
| 762 |
+
[2025-01-08 18:15:38,930][01481] RunningMeanStd input shape: (1,)
|
| 763 |
+
[2025-01-08 18:15:38,943][01481] ConvEncoder: input_channels=3
|
| 764 |
+
[2025-01-08 18:15:38,979][01481] Conv encoder output size: 512
|
| 765 |
+
[2025-01-08 18:15:38,981][01481] Policy head output size: 512
|
| 766 |
+
[2025-01-08 18:15:38,999][01481] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000104_425984.pth...
|
| 767 |
+
[2025-01-08 18:15:39,448][01481] Num frames 100...
|
| 768 |
+
[2025-01-08 18:15:39,569][01481] Num frames 200...
|
| 769 |
+
[2025-01-08 18:15:39,687][01481] Num frames 300...
|
| 770 |
+
[2025-01-08 18:15:39,851][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
| 771 |
+
[2025-01-08 18:15:39,853][01481] Avg episode reward: 3.840, avg true_objective: 3.840
|
| 772 |
+
[2025-01-08 18:15:39,876][01481] Num frames 400...
|
| 773 |
+
[2025-01-08 18:15:39,992][01481] Num frames 500...
|
| 774 |
+
[2025-01-08 18:15:40,111][01481] Num frames 600...
|
| 775 |
+
[2025-01-08 18:15:40,234][01481] Num frames 700...
|
| 776 |
+
[2025-01-08 18:15:40,377][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
|
| 777 |
+
[2025-01-08 18:15:40,379][01481] Avg episode reward: 3.840, avg true_objective: 3.840
|
| 778 |
+
[2025-01-08 18:15:40,419][01481] Num frames 800...
|
| 779 |
+
[2025-01-08 18:15:40,540][01481] Num frames 900...
|
| 780 |
+
[2025-01-08 18:15:40,662][01481] Num frames 1000...
|
| 781 |
+
[2025-01-08 18:15:40,808][01481] Avg episode rewards: #0: 3.557, true rewards: #0: 3.557
|
| 782 |
+
[2025-01-08 18:15:40,810][01481] Avg episode reward: 3.557, avg true_objective: 3.557
|
| 783 |
+
[2025-01-08 18:15:40,850][01481] Num frames 1100...
|
| 784 |
+
[2025-01-08 18:15:40,966][01481] Num frames 1200...
|
| 785 |
+
[2025-01-08 18:15:41,085][01481] Num frames 1300...
|
| 786 |
+
[2025-01-08 18:15:41,203][01481] Num frames 1400...
|
| 787 |
+
[2025-01-08 18:15:41,324][01481] Avg episode rewards: #0: 3.627, true rewards: #0: 3.627
|
| 788 |
+
[2025-01-08 18:15:41,326][01481] Avg episode reward: 3.627, avg true_objective: 3.627
|
| 789 |
+
[2025-01-08 18:15:41,390][01481] Num frames 1500...
|
| 790 |
+
[2025-01-08 18:15:41,509][01481] Num frames 1600...
|
| 791 |
+
[2025-01-08 18:15:41,634][01481] Num frames 1700...
|
| 792 |
+
[2025-01-08 18:15:41,754][01481] Num frames 1800...
|
| 793 |
+
[2025-01-08 18:15:41,936][01481] Avg episode rewards: #0: 3.998, true rewards: #0: 3.798
|
| 794 |
+
[2025-01-08 18:15:41,938][01481] Avg episode reward: 3.998, avg true_objective: 3.798
|
| 795 |
+
[2025-01-08 18:15:41,942][01481] Num frames 1900...
|
| 796 |
+
[2025-01-08 18:15:42,062][01481] Num frames 2000...
|
| 797 |
+
[2025-01-08 18:15:42,184][01481] Num frames 2100...
|
| 798 |
+
[2025-01-08 18:15:42,315][01481] Num frames 2200...
|
| 799 |
+
[2025-01-08 18:15:42,470][01481] Avg episode rewards: #0: 3.972, true rewards: #0: 3.805
|
| 800 |
+
[2025-01-08 18:15:42,472][01481] Avg episode reward: 3.972, avg true_objective: 3.805
|
| 801 |
+
[2025-01-08 18:15:42,497][01481] Num frames 2300...
|
| 802 |
+
[2025-01-08 18:15:42,621][01481] Num frames 2400...
|
| 803 |
+
[2025-01-08 18:15:42,739][01481] Num frames 2500...
|
| 804 |
+
[2025-01-08 18:15:42,844][01481] Avg episode rewards: #0: 3.770, true rewards: #0: 3.627
|
| 805 |
+
[2025-01-08 18:15:42,846][01481] Avg episode reward: 3.770, avg true_objective: 3.627
|
| 806 |
+
[2025-01-08 18:15:42,923][01481] Num frames 2600...
|
| 807 |
+
[2025-01-08 18:15:43,043][01481] Num frames 2700...
|
| 808 |
+
[2025-01-08 18:15:43,164][01481] Num frames 2800...
|
| 809 |
+
[2025-01-08 18:15:43,253][01481] Avg episode rewards: #0: 3.659, true rewards: #0: 3.534
|
| 810 |
+
[2025-01-08 18:15:43,254][01481] Avg episode reward: 3.659, avg true_objective: 3.534
|
| 811 |
+
[2025-01-08 18:15:43,354][01481] Num frames 2900...
|
| 812 |
+
[2025-01-08 18:15:43,475][01481] Num frames 3000...
|
| 813 |
+
[2025-01-08 18:15:43,599][01481] Num frames 3100...
|
| 814 |
+
[2025-01-08 18:15:43,721][01481] Num frames 3200...
|
| 815 |
+
[2025-01-08 18:15:43,864][01481] Avg episode rewards: #0: 3.861, true rewards: #0: 3.639
|
| 816 |
+
[2025-01-08 18:15:43,868][01481] Avg episode reward: 3.861, avg true_objective: 3.639
|
| 817 |
+
[2025-01-08 18:15:43,899][01481] Num frames 3300...
|
| 818 |
+
[2025-01-08 18:15:44,016][01481] Num frames 3400...
|
| 819 |
+
[2025-01-08 18:15:44,134][01481] Num frames 3500...
|
| 820 |
+
[2025-01-08 18:15:44,260][01481] Num frames 3600...
|
| 821 |
+
[2025-01-08 18:15:44,392][01481] Avg episode rewards: #0: 3.859, true rewards: #0: 3.659
|
| 822 |
+
[2025-01-08 18:15:44,394][01481] Avg episode reward: 3.859, avg true_objective: 3.659
|
| 823 |
+
[2025-01-08 18:16:05,322][01481] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
|