Hugging Face's logo

orepin
/
ppo-LunarLander-v2

Reinforcement Learning
stable-baselines3
TensorBoard
LunarLander-v2
deep-reinforcement-learning
Eval Results
Model card Files
xet
Metrics Community
orepin commited on
Commit
8d35ed5
·
1 Parent(s): 3243f36

Push agent to the Hub

Browse files
Files changed (5) hide show
  1. README.md +8 -8
  2. logs/events.out.tfevents.1685099188.Almiras-MacBook-Air.local.6910.0 +3 -0
  3. model.pt +1 -1
  4. replay.mp4 +0 -0
  5. results.json +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -144.39 +/- 101.05
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -30,22 +30,22 @@ model-index:
30
  ```python
31
  {'exp_name': 'ppo'
32
  'gym_id': 'LunarLander-v2'
33
- 'learning_rate': 0.0001
34
  'seed': 1
35
- 'total_timesteps': 10000
36
  'torch_deterministic': True
37
  'cuda': True
38
  'track': False
39
  'wandb_project_name': 'ppo-implementation-details'
40
  'wandb_entity': None
41
  'capture_video': False
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
@@ -56,7 +56,7 @@ model-index:
56
  'target_kl': None
57
  'push_to_hf': False
58
  'repo_id': 'orepin/ppo-LunarLander-v2'
59
- 'batch_size': 512
60
  'minibatch_size': 128}
61
  ```
62
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 68.44 +/- 80.33
21
  name: mean_reward
22
  verified: false
23
  ---
 
30
  ```python
31
  {'exp_name': 'ppo'
32
  'gym_id': 'LunarLander-v2'
33
+ 'learning_rate': 0.00025
34
  'seed': 1
35
+ 'total_timesteps': 1000000
36
  'torch_deterministic': True
37
  'cuda': True
38
  'track': False
39
  'wandb_project_name': 'ppo-implementation-details'
40
  'wandb_entity': None
41
  'capture_video': False
42
+ 'num_envs': 8
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
+ 'gae_lambda': 0.98
48
+ 'num_minibatches': 64
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
56
  'target_kl': None
57
  'push_to_hf': False
58
  'repo_id': 'orepin/ppo-LunarLander-v2'
59
+ 'batch_size': 8192
60
  'minibatch_size': 128}
61
  ```
62
 
logs/events.out.tfevents.1685099188.Almiras-MacBook-Air.local.6910.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f65ec5771a26073b06de036c2792a997c790c15c0bd0370969f413c749eacb9
3
+ size 313251
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1600e1a2d7f8c81d6ea02e571b94b3997953732ae5a80a06d69fccbb68b5cb3a
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8b95dc822f70e7735d1361612f3b610d0f7774a724731ef63d8e28ee2379f2
3
  size 42469
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": -144.39302475844147, "std_reward": 101.05387854398585, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T11:20:54.763477"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 68.43948222348806, "std_reward": 80.33388124269412, "n_evaluation_episodes": 30, "eval_datetime": "2023-05-26T12:39:52.697511"}