Hugging Face's logo

YusufTree
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
YusufTree commited on
Commit
80e6575
·
1 Parent(s): 5190447

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 303.50 +/- 129.60
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 200000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 152.50 +/- 92.18
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1048706378
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 213054211
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b36bebd155f588be8f7882ad86c9281ec33ac95c2394978a5c287ab98722dbbc
3
- size 27220204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9530f17360a42c1817a2adec2044c75294c351a81c1d3b0637bf6821569e46c7
3
+ size 27219650
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47729aaea2e9038ba9795dc106531550a7f886f46ec09f7c7b53978803cd3865
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325301a58f56fbf3209ab9d0c733e34d1221f6fe9971539dd2f8c9e47f160191
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7ea81b7288e3e4aa27207836bbc8e8c3859fb4ccd6db93cc33c68b68e7ccc5f
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db982bfc27b8e6e49c67c678f6b8f7d18b84b451946694496ba9f7aae34aadca
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0a2
4
  - PyTorch: 2.1.0+cu121
5
- - GPU Enabled: True
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0a2
4
  - PyTorch: 2.1.0+cu121
5
+ - GPU Enabled: False
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50f5c210e3f5ba85dedebdfeb965714caffc6580997a9e99deb03b5cf6930c6
3
- size 275420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe42344aac7901c6d1e34e5fd211228d57d34575187e3037d8d93a038cb4b54
3
+ size 255326
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 303.5, "std_reward": 129.59648914997658, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-28T14:50:19.221459"}
 
1
+ {"mean_reward": 152.5, "std_reward": 92.17510509893656, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T18:04:43.523173"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14db86cafdd898e175f218d4ac105ee4a7a2feacb54dd62f617d4d2e509d6a10
3
- size 9405
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12dd191cbfad410f3f970df60db9efb576fe6c9a37b79b05eb0f1c489412cd49
3
+ size 7542