c72599 commited on
Commit
a2f149c
1 Parent(s): d91495c

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: -158.10 +/- 105.68
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
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'c72599/LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -113.70 +/- 40.79
21
  name: mean_reward
22
  verified: false
23
  ---
 
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': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'c72599/LunarLander-v2'
58
+ 'batch_size': 1024
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1689848599.94dbf6c03cb8.13632.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63fce884820cc06378fbcda5abe2d0f627623c5066444f990569cf12de56389
3
+ size 157864
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cc9966d1cdbff9994e0b52c726d56b8ae4da854df573497da7b2359c5cbd7b3
3
- size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33856b0d9b559404defac6b113cd75d1f3416211b55f7eb5cd02c0c6897ebf6a
3
+ size 78363
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": -158.10319748116177, "std_reward": 105.6809529418321, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T10:20:26.028491"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -113.69566542273034, "std_reward": 40.79014072482425, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T10:24:43.081766"}