arhamk commited on
Commit
dd6435b
1 Parent(s): c69c269

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: -198.34 +/- 74.34
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,14 +38,14 @@ 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': 1024
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.999
47
- 'gae_lambda': 0.98
48
- 'num_minibatches': 64
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
@@ -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': 4096
59
- 'minibatch_size': 64}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -54.49 +/- 34.35
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
+ 'learning_rate': 0.003
42
+ 'num_envs': 16
43
+ 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.98
47
+ 'gae_lambda': 0.95
48
+ 'num_minibatches': 512
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'arhamk/ppo-LunarLander-v2-2'
58
+ 'batch_size': 8192
59
+ 'minibatch_size': 16}
60
  ```
61
 
logs/events.out.tfevents.1718026610.887b5cfc0142.17454.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6300fdc1f15e0b1b13091ef3d58fd2c91af1f709b943a8690b020dc552100a
3
+ size 59923
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcbff33b0526b566a2e6acb6848b2f96fcf006fc2e414e4db47250a82fc14af6
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a58fe495019102aff7d9e1c3e03717aac57da4caa78067a973a7c79d87891e
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": -198.33504571134165, "std_reward": 74.34280086641499, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:29:37.193386"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -54.489404952999905, "std_reward": 34.35335335448864, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:38:13.120145"}