Hugging Face's logo

davideaguglia
/
ppo-BreakoutNoFrameskip-v4-V2-try

Reinforcement Learning
stable-baselines3
BreakoutNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
davideaguglia commited on
Commit
60eee43
•
1 Parent(s): 3cfc74a

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. args.yml +2 -4
  3. ppo-BreakoutNoFrameskip-v4.zip +2 -2
  4. ppo-BreakoutNoFrameskip-v4/data +0 -0
  5. ppo-BreakoutNoFrameskip-v4/policy.optimizer.pth +1 -1
  6. ppo-BreakoutNoFrameskip-v4/policy.pth +1 -1
  7. replay.mp4 +2 -2
  8. results.json +1 -1
  9. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 351.90 +/- 30.44
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 385.80 +/- 35.80
20
  name: mean_reward
21
  verified: false
22
  ---
args.yml CHANGED
@@ -2,15 +2,13 @@
2
  - - - algo
3
  - ppo
4
  - - conf_file
5
- - null
6
  - - device
7
  - auto
8
  - - env
9
  - BreakoutNoFrameskip-v4
10
  - - env_kwargs
11
  - null
12
- - - eval_env_kwargs
13
- - null
14
  - - eval_episodes
15
  - 5
16
  - - eval_freq
@@ -56,7 +54,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2955100659
60
  - - storage
61
  - null
62
  - - study_name
 
2
  - - - algo
3
  - ppo
4
  - - conf_file
5
+ - /kaggle/input/ppo-yml/ppo.yml
6
  - - device
7
  - auto
8
  - - env
9
  - BreakoutNoFrameskip-v4
10
  - - env_kwargs
11
  - null
 
 
12
  - - eval_episodes
13
  - 5
14
  - - eval_freq
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 454401134
58
  - - storage
59
  - null
60
  - - study_name
ppo-BreakoutNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dfa015070756c4044dcf021e8143184bacfb2da58c38b07c0f1c7d1ecabafb7
3
- size 20427914
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ae018be1d8e64b463faebd351e0ad8b1f2ff5b0cec1eb2066ea43ff80c2d30
3
+ size 20428446
ppo-BreakoutNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
ppo-BreakoutNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f3e32c215f2e976c19ad5ad6f438d2b9437c4fdacad5abaf918cc20eca7d97
3
  size 13503274
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f2380bdbb84fc1da743601c48ef04b41781024c3c062c5c35f6cb67a1fd51b
3
  size 13503274
ppo-BreakoutNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:614278965a177bca35d447ce8cb941e32f5a5ee5d7549bf9bc0cff15194c0873
3
  size 6753778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460ac91ac4007ab314abf95bb98a4691965c9ffa4185933dcd0edf04d15b6e94
3
  size 6753778
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0df27c1c422164d0386a31a6cc09540205d074b07d9113cfb5e15ba3b2b7c535
3
- size 76389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe41726eea8ccd6041b22b84990036946b62e9e9b17850955184e36a796b5ced
3
+ size 74286
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 351.9, "std_reward": 30.444868204674492, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-20T08:15:49.944737"}
 
1
+ {"mean_reward": 385.8, "std_reward": 35.79888266412794, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-20T08:21:32.244553"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38b1cae32c41af8a8adc0d366e22d763f5342bea3ca0a0f5b7168842c5f63f68
3
- size 224483
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0bf8142bd05d4d343c792915f20b857dd855a13803f8c1d659f3e2342c1d82
3
+ size 237880