Zionamsalem commited on
Commit
ce73b50
·
verified ·
1 Parent(s): ba40f0e

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: -186.83 +/- 116.96
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -28,7 +28,7 @@ model-index:
28
 
29
  # Hyperparameters
30
  ```python
31
- {'exp_name': 'ppo_optimized'
32
  'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
@@ -37,25 +37,25 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
- 'learning_rate': 0.0003
42
- 'num_envs': 8
43
- 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
- 'update_epochs': 3
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
- 'ent_coef': 0.005
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
- 'target_kl': 0.015
57
  'repo_id': 'Zionamsalem/LLV2'
58
- 'batch_size': 2048
59
- 'minibatch_size': 512}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -139.45 +/- 88.91
21
  name: mean_reward
22
  verified: false
23
  ---
 
28
 
29
  # Hyperparameters
30
  ```python
31
+ {'exp_name': 'ppo'
32
  'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
 
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': 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
53
+ 'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
+ 'target_kl': None
57
  'repo_id': 'Zionamsalem/LLV2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1740321509.57e0e4a6823e.8334.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bae6429fd4ed2fc4a39ef72ebc3b1138a094075db15d18bd7cc9b5c144644e
3
+ size 221305
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:064b494bef98697f62ac684ad914aac568c106059e062d09ce1bd48202935b31
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d7dd5e3988bbef80f64243ce6cc4003af98cb92a17fa58a0c9c43a24eda687
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": -186.82807786633282, "std_reward": 116.96067705206202, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T14:36:33.579602"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -139.44708469932576, "std_reward": 88.90981378219666, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T14:39:46.627658"}