Hans14 commited on
Commit
586843b
·
1 Parent(s): 24d7b96

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: -58.16 +/- 47.90
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,25 +37,25 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 100000
41
- 'learning_rate': 0.0003
42
  'num_envs': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.99
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
- 'clip_coef': 0.2
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Hans14/LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -169.73 +/- 96.53
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 200000
41
+ 'learning_rate': 0.0001
42
  'num_envs': 4
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.95
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
+ 'clip_coef': 0.1
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Hans14/LunarLander-v2'
58
+ 'batch_size': 1024
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1689490888.8981986e6198.31971.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256d041e7c541e73f1c95564edc6507251d8cbadeba575149487064a245b2a98
3
+ size 323631
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac3a286e0e3d3a17acf2e5bbec8251c943276bac4d8871122da6db79d6d6ddbb
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d48e06c7d6148401181153f1475ab8b0e5911286169190aca1d72cced70967
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": -58.15821611567151, "std_reward": 47.89611705004283, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T06:50:11.034057"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -169.72708051838686, "std_reward": 96.52854253023148, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:04:17.030388"}