wasimar commited on
Commit
27f2cc1
·
1 Parent(s): 1011974

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: -186.90 +/- 122.88
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,9 +37,9 @@ 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': 128
44
  'anneal_lr': True
45
  'gae': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'wasimar/ppo-CartPole-v1'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -60.72 +/- 82.90
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 24
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'wasimar/ppo-CartPole-v1'
58
+ 'batch_size': 3072
59
+ 'minibatch_size': 768}
60
  ```
61
 
logs/events.out.tfevents.1684961720.0d352bfbd555.15768.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3db63e737bd827a3d13fad1015caed1f3da49205e49ba17fb6e94ee887b34ca
3
+ size 406227
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:352b29f3c3f4d4e2a36b5743be7dd26cde2d9e8abe40e72c375dcb319e6f5ecc
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0808706948eee7fc9988d0a8c556cef17d2b46aff4d7c610626bde2e8c9937
3
  size 42597
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": -186.89513946028228, "std_reward": 122.8845319282402, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-24T20:42:08.655744"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -60.71512584512732, "std_reward": 82.90309997347869, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-24T21:00:42.431741"}