arhamk commited on
Commit
e0065c5
1 Parent(s): d17cdcc

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: -241.01 +/- 140.47
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,15 +38,15 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
- 'learning_rate': 1e-05
42
  'num_envs': 4
43
- 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.99
47
- 'gae_lambda': 0.95
48
  'num_minibatches': 16
49
- 'update_epochs': 8
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': 'arhamk/ppo-LunarLander-v2-2'
58
- 'batch_size': 2048
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -200.37 +/- 73.91
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
+ 'learning_rate': 2e-05
42
  'num_envs': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
+ 'gae_lambda': 0.98
48
  'num_minibatches': 16
49
+ 'update_epochs': 4
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': 'arhamk/ppo-LunarLander-v2-2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1718025938.887b5cfc0142.14571.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfbadeff200db8a683c5a1c6e32d0dc72670cf155eba3140687c49be38d6d7bb
3
+ size 70776
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f07b1b08be38f4670bcf36173b8ffae2cccd31c81bb92664307eaa120d0f012
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c2b4f6bbec26d6d381fb204a07994e8da94729d0e7c86b50317168857c0ee5
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": -241.0094816404568, "std_reward": 140.47431516175723, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:19:50.546744"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -200.36639274859556, "std_reward": 73.91482615132544, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:26:17.286255"}