bobobert4 commited on
Commit
59ea422
1 Parent(s): 0159ae9

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: -99.00 +/- 77.65
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': 250000
41
- 'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 200
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': 'bobobert4/ppo-clean-LunarLander-v2'
58
- 'batch_size': 800
59
- 'minibatch_size': 200}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -4.59 +/- 132.08
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 150000
41
+ 'learning_rate': 0.0001
42
  'num_envs': 4
43
+ 'num_steps': 8
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
+ 'num_minibatches': 6
49
+ 'update_epochs': 8
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': 'bobobert4/ppo-clean-LunarLander-v2'
58
+ 'batch_size': 32
59
+ 'minibatch_size': 5}
60
  ```
61
 
logs/events.out.tfevents.1690354936.1994278cbccb.31520.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edcd98bda59d35a3923194bfb47882bf722ad2b7922e7067ae176a95c71bc062
3
+ size 2477222
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3591aee815b94e82a4eed75774dfc6b51ae26cff3fa5bc1893ad96598a15d5f
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e5aa6147a253793dfb20e08060d0d999a402515ce5f9dafccc6a615e2b45dc
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": -99.00299708927268, "std_reward": 77.65035114062258, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-26T05:25:34.639300"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -4.594062033781432, "std_reward": 132.07967002708847, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-26T07:26:30.852803"}