xian79 commited on
Commit
4d2cd4c
·
1 Parent(s): 26aa24d

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: -166.93 +/- 143.45
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ 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
46
  'gamma': 0.99
@@ -50,12 +50,12 @@ model-index:
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': 'xian79/ppo-LunarLander-v2.8'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -1.74 +/- 68.05
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': 0.001
42
  'num_envs': 4
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
+ 'ent_coef': 0.03
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'xian79/ppo-LunarLander-v2.8'
58
+ 'batch_size': 1024
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1689917981.2364148aff98.3332.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c856f2557e9039aa114c3e6c534ab3b61fa97199c5f984c5f606ffad65e8ddae
3
+ size 173509
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9258b5833371718b1ea42a9618208402533883c972690ccac738aeea863cfb1e
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": -166.92660237344973, "std_reward": 143.45149316890283, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T00:34:44.508927"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -1.7415937480253632, "std_reward": 68.04936794891167, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-21T05:45:41.805245"}