Hugging Face's logo

MattStammers
/
ppo-BreakoutNoFrameskip-v4-overtrained

Reinforcement Learning
stable-baselines3
BreakoutNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
MattStammers commited on
Commit
9a48df1
•
1 Parent(s): 393617d

Initial commit

Browse files
Files changed (8) hide show
  1. README.md +1 -3
  2. ppo-BreakoutNoFrameskip-v4.zip +2 -2
  3. ppo-BreakoutNoFrameskip-v4/data +0 -0
  4. ppo-BreakoutNoFrameskip-v4/policy.optimizer.pth +1 -1
  5. ppo-BreakoutNoFrameskip-v4/policy.pth +1 -1
  6. replay.mp4 +2 -2
  7. results.json +1 -1
  8. 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: 558.40 +/- 191.19
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -82,5 +82,3 @@ OrderedDict([('batch_size', 256),
82
  ```python
83
  {'render_mode': 'rgb_array'}
84
  ```
85
-
86
- This one is presently similar to my last one so there is more work to go still
 
16
  type: BreakoutNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 472.40 +/- 113.77
20
  name: mean_reward
21
  verified: false
22
  ---
 
82
  ```python
83
  {'render_mode': 'rgb_array'}
84
  ```
 
 
ppo-BreakoutNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74d882bee9c97ca5b8c8fa76941cd800fedb24c1a9d7172849e92405e62f2ad8
3
- size 20425198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963780344b17f59a767b8bac2cb3f4d2ef0427596a6957b30b8ba04cbc28a0a9
3
+ size 20425207
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 sha256:7d82340de607706f99aca440c2ff4c16165556b254a0729d4ab4bf431edc03fc
3
  size 13502841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02e5a6e6ede9837baf29a0f74bddff2317a4e9b7a77c09b95a59b14821ee0e8
3
  size 13502841
ppo-BreakoutNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c12643d8f4863873ca341d7152ff749384b06d94c2237ce04dbb7b27720a84c3
3
  size 6753345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31f6dac049c0d0fca351fa5b8cd2d1b525b93f0ab8568978ccd8b06592b047b
3
  size 6753345
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26c0002277d3686a922618d1827b41fbc697182ae51c654fbc7153e11bbe4b24
3
- size 76579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce440f439c4baf4bc9e5030d17977d8506b2a61d73944d3787ee8327684a887
3
+ size 80488
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 558.4, "std_reward": 191.18535508767403, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-05T06:46:12.134867"}
 
1
+ {"mean_reward": 472.4, "std_reward": 113.7718770171258, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-06T07:49:22.187719"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4a0986b44a9fe808191c5e482ede16e44e011eb8a697fc4b2bbb0ac279559d0
3
- size 562469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de41f1eb3a0bc03b20c8813a78d20aedc6962404980c751dfdf744dc0986a61
3
+ size 807724