Ari8 commited on
Commit
58cb864
·
verified ·
1 Parent(s): 9497742

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -182.38 +/- 62.36
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -40,7 +40,7 @@ model-index:
40
  'total_timesteps': 50000
41
  'learning_rate': 1e-05
42
  'num_envs': 6
43
- 'num_steps': 165
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Ari8/ppo-LunarLander-v2_unit8'
58
- 'batch_size': 990
59
- 'minibatch_size': 247}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -176.55 +/- 95.51
21
  name: mean_reward
22
  verified: false
23
  ---
 
40
  'total_timesteps': 50000
41
  'learning_rate': 1e-05
42
  'num_envs': 6
43
+ 'num_steps': 188
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Ari8/ppo-LunarLander-v2_unit8'
58
+ 'batch_size': 1128
59
+ 'minibatch_size': 282}
60
  ```
61
 
logs/events.out.tfevents.1746578609.b45e59692ef7.16857.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f897debd361d1c7c1d4695c266fd30845a7139174f9bc68c17f4dfa38adbffad
3
+ size 86804
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:805cc3f8d7a9e068e4c173e54262a7510367033f8e2e31a4cab03066c9379f77
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432f7a431e47fe629ed186b1cb4ca1c6a9e47faee79285a4caf635cd2a6f6394
3
  size 43026
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -182.37665860979823, "std_reward": 62.3579062790844, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:42:12.031663"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -176.55009839028313, "std_reward": 95.50646055675692, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:44:00.827494"}