Hugging Face's logo

ThomasSimonini
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
ThomasSimonini HF staff commited on
Commit
fb60f6f
•
1 Parent(s): 6d62c03

Initial commit

Browse files
Files changed (8) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  7. results.json +1 -1
  8. 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: 6.00 +/- 9.17
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 10000.0),
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: 153.00 +/- 84.68
20
  name: mean_reward
21
  verified: false
22
  ---
 
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
- - 3958810720
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2679771001
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
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:a7c9bf4358bf89fdf5a760b196deadff9905b42b5b1eda63b9537e6338eebd65
3
- size 13710057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d2c023ba4d462173873385b112c1d903d470367c057082fc4febcea0a9e4d6
3
+ size 13711405
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34d57bbb9d8a1ed7580ddd62130f35447d23a25e026521976a31e3555f1f3cb2
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d97b2f22222a9a8b673851c5ac411634984aae2212d5bba2466aac37a6a8f6a
3
  size 13504937
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 6.0, "std_reward": 9.16515138991168, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-04T08:15:13.257777"}
 
1
+ {"mean_reward": 153.0, "std_reward": 84.6817571853584, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-04T09:15:32.226994"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cb25b8059114a1995f437cfb6a2ca08b87670e89f95db40d5c459db0cff2789
3
- size 649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9268c22ecfbca5861c6dcd41566a8b075a8956020405a42f9b2710c3e53e480f
3
+ size 2295