Hugging Face's logo

davideaguglia
/
ppo-BreakoutNoFrameskip-v4

Reinforcement Learning
stable-baselines3
BreakoutNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
davideaguglia commited on
Commit
84423fb
•
1 Parent(s): 927cee1

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. ppo-BreakoutNoFrameskip-v4.zip +2 -2
  5. ppo-BreakoutNoFrameskip-v4/data +0 -0
  6. ppo-BreakoutNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. ppo-BreakoutNoFrameskip-v4/policy.pth +1 -1
  8. ppo-BreakoutNoFrameskip-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: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 44.50 +/- 63.29
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 256),
72
  ('n_envs', 8),
73
  ('n_epochs', 4),
74
  ('n_steps', 128),
75
- ('n_timesteps', 2000000.0),
76
  ('policy', 'CnnPolicy'),
77
  ('vf_coef', 0.5),
78
  ('normalize', False)])
 
16
  type: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 385.80 +/- 35.80
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('n_envs', 8),
73
  ('n_epochs', 4),
74
  ('n_steps', 128),
75
+ ('n_timesteps', 10000000.0),
76
  ('policy', 'CnnPolicy'),
77
  ('vf_coef', 0.5),
78
  ('normalize', False)])
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2163266192
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 454401134
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - n_steps
19
  - 128
20
  - - n_timesteps
21
- - 2000000.0
22
  - - policy
23
  - CnnPolicy
24
  - - vf_coef
 
18
  - - n_steps
19
  - 128
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - policy
23
  - CnnPolicy
24
  - - vf_coef
ppo-BreakoutNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62493dd99dbaa927a35966ab6e56e75d25a5e7fc029b68f54f3d4eb14ca00c26
3
- size 20427911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66341c795248fee76529feccf7ce481c2a13f9fd2f59eda8f13df45ad9facce
3
+ size 20427914
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:d92f519b03414dade27ebe7101497fef8fffb053f1e0dcb124821460084018d5
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:ec64d75577ef51206f99ece34fab76c4ced183acb8edeb96e65d0f625f16e9cc
3
  size 6753778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460ac91ac4007ab314abf95bb98a4691965c9ffa4185933dcd0edf04d15b6e94
3
  size 6753778
ppo-BreakoutNoFrameskip-v4/system_info.txt CHANGED
@@ -1,4 +1,4 @@
1
- - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.2
4
  - PyTorch: 2.2.1+cu121
 
1
+ - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.2
4
  - PyTorch: 2.2.1+cu121
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c44502a94ccfe4ad3ca4a9a1bc5d75e7e15f35a6a7c1a40f4e0116e2e9ddee5
3
- size 73998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe41726eea8ccd6041b22b84990036946b62e9e9b17850955184e36a796b5ced
3
+ size 74286
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 44.5, "std_reward": 63.28862457029699, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-14T16:22:09.033403"}
 
1
+ {"mean_reward": 385.8, "std_reward": 35.79888266412794, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T18:57:17.573944"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e392acec30cab22b218fcd52cc461848724cea86939143c6ede3d9a8dd53b0
3
- size 103089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f08b96200ea834570a10da606c9a9487b22240ef47716419d04495bacf02b7
3
+ size 237880