rahatchd commited on
Commit
4be0737
·
verified ·
1 Parent(s): 8a88ebb

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: -206.66 +/- 121.18
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 250
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': 'rahatchd/ppo-from-scratch-LunarLander-v2'
58
- 'batch_size': 1000
59
- 'minibatch_size': 250}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -165.30 +/- 107.01
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 5000
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'rahatchd/ppo-from-scratch-LunarLander-v2'
58
+ 'batch_size': 20000
59
+ 'minibatch_size': 5000}
60
  ```
61
 
logs/events.out.tfevents.1733609777.d287217ef4d7.7178.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af18380434ce7cac2ad36f7747bb329bbdf014758da2af14843e1a2dc5941b98
3
+ size 1125668
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a41308bdd6cb34f995e226efa3923f74194a3d903239ce74f0f72c6d6fbb081e
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671be20b3b850304ce8b2e9f5b18c1cff64dc67bbc499ef890d48c7fbe90a7d3
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": -206.65589446187087, "std_reward": 121.17618685428602, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-07T22:14:51.949375"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -165.29679684884556, "std_reward": 107.00825532820417, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-07T22:27:14.959757"}