apple9855 commited on
Commit
517bf70
·
verified ·
1 Parent(s): 44ab830

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: -124.93 +/- 83.02
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': 100000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'apple9855/ppo-cleanrl-lunarlander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -88.66 +/- 96.91
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': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'apple9855/ppo-cleanrl-lunarlander-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1727600267.50c4b48e3dc0.12565.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20fd143c16bf7b5f166d4ebc6a2326530bb969c8edd27f244917a9373f1d227
3
+ size 536389
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da85c2655fa22eceb08f285bb6687b81436a7f944348338edb35256ae558b6fb
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4af99017a99d307723560614af1ade828a307ae97ebbcb3ff9b7639ceb74582
3
  size 43026
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": -124.9275477196552, "std_reward": 83.02110562522213, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-29T08:48:04.356107"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -88.65743429539637, "std_reward": 96.91273379664419, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-29T09:03:32.436726"}