ben-yu commited on
Commit
7d0de24
1 Parent(s): edd22e0

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: -134.90 +/- 55.10
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,7 +39,7 @@ model-index:
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': 'ben-yu/LunarLander-v2-ppo'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -154.08 +/- 71.47
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 12
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'ben-yu/LunarLander-v2-ppo'
58
+ 'batch_size': 1536
59
+ 'minibatch_size': 384}
60
  ```
61
 
logs/events.out.tfevents.1676773165.5e7fcccfc678.3331.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e9e1611ccf92fcd568b5b8d6034f143da44c4ab6fb6ddadc3bea8aa456be09
3
+ size 75527
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29edfe0b2c6fd6034e822d908cd363a255a089d11070b6194f97ba22a3c01ac
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": -134.89670261954993, "std_reward": 55.102553677235605, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:16:06.083236"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -154.08126863359044, "std_reward": 71.47305763224958, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:19:52.511280"}