Ari8 commited on
Commit
ae179b7
·
verified ·
1 Parent(s): 00544ee

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: -146.68 +/- 107.02
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -40,13 +40,13 @@ model-index:
40
  'total_timesteps': 50000
41
  'learning_rate': 1e-05
42
  'num_envs': 6
43
- 'num_steps': 98
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
- 'num_minibatches': 4
49
- 'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
@@ -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': 588
59
- 'minibatch_size': 147}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -141.77 +/- 91.30
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
47
  'gae_lambda': 0.95
48
+ 'num_minibatches': 6
49
+ 'update_epochs': 6
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
 
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': 188}
60
  ```
61
 
logs/events.out.tfevents.1746579519.b45e59692ef7.20867.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b12c8d35963fbfca7328f4ad48d4b5c524b00e0444402e6d79760f79c19414c
3
+ size 86428
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40aeb8c1755a53aec3b776e8c628e6a273645c483285c7f4b9e476a3f08d3622
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47309c5fd3362d304b06b17a07089a051bad997e3a5ee70adfdde21256f9b780
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": -146.67560210914849, "std_reward": 107.02481737452253, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:56:28.646860"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -141.77458028260435, "std_reward": 91.30179115837801, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:59:15.574462"}