hui168 commited on
Commit
cf54044
1 Parent(s): ee588da

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: -20.59 +/- 93.87
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,12 +37,13 @@ model-index:
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': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
- 'gamma': 0.99
 
46
  'gae_lambda': 0.95
47
  'num_minibatches': 4
48
  'update_epochs': 4
@@ -53,9 +54,8 @@ model-index:
53
  'vf_coef': 0.5
54
  'max_grad_norm': 0.5
55
  'target_kl': None
 
56
  'batch_size': 512
57
- 'minibatch_size': 128
58
- 'num_iterations': 976
59
- 'repo_id': 'hui168/ppo-LunarLander-v2-from-scratch'}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 132.06 +/- 46.81
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 2000000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
+ 'gae': True
46
+ 'gamma': 0.99999
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
 
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
+ 'repo_id': 'hui168/ppo-LunarLander-v2-from-scratch'
58
  'batch_size': 512
59
+ 'minibatch_size': 128}
 
 
60
  ```
61
 
logs/events.out.tfevents.1712866688.e9e41f7c5b7d.3430.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de94293a2101cfd69b935dafe7e75fe880b87276fcb51280e8f3117596e49c21
3
+ size 2478958
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0b3aa6e90acfc619f24694b5c2da8db9a401ed63e61d3b395dcd0cad5017949
3
- size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7724abd1480732d3ec310d78c76da7eca3f13e01f7fc619206d5b5910bef2376
3
+ size 42898
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": -20.586317352556733, "std_reward": 93.8742911527907, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-10T23:19:28.559560"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 132.06084617443258, "std_reward": 46.80571882245905, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-11T21:19:57.836045"}