kinkpunk commited on
Commit
cdeb3d2
1 Parent(s): 4047cfc

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: -55.80 +/- 93.24
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,9 +38,9 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 550000
41
- 'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 32
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': 'kinkpunk/PPO-LunarLander'
58
- 'batch_size': 128
59
- 'minibatch_size': 32}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -41.69 +/- 53.75
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 550000
41
+ 'learning_rate': 0.0003
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': 'kinkpunk/PPO-LunarLander'
58
+ 'batch_size': 1024
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1676837579.e00ba7557307.30937.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc735344ddc877f82ed8d68ffd838b2029e848c2deb66cbf01693ec5641e03f
3
+ size 422378
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7af0214800ada59a1a4fc3d93cb2c137eab1631b43e8dd909dcf0c46bb5ca13b
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172fe45cbf8992f0cb1f5d6ced0dcefcf4bd151c22304f4c22cf086d231537be
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": -55.79561226201317, "std_reward": 93.24380743018068, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T20:12:03.021254"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -41.692552472580324, "std_reward": 53.74714583676262, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T20:29:28.060964"}