Cryxim commited on
Commit
5c9ee92
·
verified ·
1 Parent(s): 52ae60d

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: -158.41 +/- 89.51
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,15 +38,15 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
- 'learning_rate': 2e-05
42
  'num_envs': 4
43
- 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.97
47
- 'gae_lambda': 0.93
48
  'num_minibatches': 5
49
- 'update_epochs': 3
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': 'Cryxim/ppo-LunarLanderV2'
58
- 'batch_size': 1024
59
- 'minibatch_size': 204}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -75.67 +/- 52.80
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
+ 'learning_rate': 0.002
42
  'num_envs': 4
43
+ 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.995
47
+ 'gae_lambda': 0.95
48
  'num_minibatches': 5
49
+ 'update_epochs': 5
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': 'Cryxim/ppo-LunarLanderV2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 102}
60
  ```
61
 
logs/events.out.tfevents.1725113369.bf6224b6eef2.8098.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6dc76bbb77381458a8505b8460e0b7d3cfce1fb4b402f2c1f5dc372d46433e
3
+ size 106427
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:044d2ba3f43cc3558664ad6be3f6fd78a0968541a2d3b218ebbd41de548a51eb
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a18f123adc950443b32f5ce5ed9471af66bf67c2c3dd3092000814cbcc5241bd
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": -158.40772154424025, "std_reward": 89.510746105138, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-31T14:08:40.723653"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -75.6661252765131, "std_reward": 52.8039418081801, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-31T14:10:19.059639"}