jjhonny commited on
Commit
dabdacc
1 Parent(s): e1f18bf

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: -111.15 +/- 50.39
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,16 +37,16 @@ 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
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
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jjhonny/LundarLander-v2-custom'
58
- 'batch_size': 512
59
  'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -51.51 +/- 93.21
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
41
+ 'learning_rate': 0.0003
42
+ 'num_envs': 1024
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
+ 'num_minibatches': 1024
49
+ 'update_epochs': 6
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jjhonny/LundarLander-v2-custom'
58
+ 'batch_size': 131072
59
  'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1688532790.b5cab0aab5c1.51708.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185d109e6f4e1b9930a13b66b4fed110820db0bf5e2eaa7f55db671e302770d6
3
+ size 105533
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5474aae4cc0d8669583d102be61d425b33b06b7b07d34411b9508052b6239d8
3
- size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8dcb4194d0f0fad6670694683480f7843e06d91451e12faf5785a20228da389
3
+ size 553189
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": -111.15393189772658, "std_reward": 50.38975110405267, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T04:47:49.181406"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -51.50794115983897, "std_reward": 93.20573428963354, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T04:56:43.118514"}