Terence3927 commited on
Commit
328adfb
1 Parent(s): 2f7d62e

Push Reinforce agent to the Hub

Browse files
README.md CHANGED
@@ -1,10 +1,11 @@
1
  ---
2
- library_name: stable-baselines3
3
  tags:
4
  - LunarLander-v2
 
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
7
- - stable-baselines3
 
8
  model-index:
9
  - name: PPO
10
  results:
@@ -16,22 +17,46 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 68.54 +/- 89.22
20
  name: mean_reward
21
  verified: false
22
  ---
23
 
24
- # **PPO** Agent playing **LunarLander-v2**
25
- This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
- using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
 
28
- ## Usage (with Stable-baselines3)
29
- TODO: Add your code
30
-
31
-
32
- ```python
33
- from stable_baselines3 import ...
34
- from huggingface_sb3 import load_from_hub
35
-
36
- ...
37
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  tags:
3
  - LunarLander-v2
4
+ - ppo
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
7
+ - custom-implementation
8
+ - deep-rl-class
9
  model-index:
10
  - name: PPO
11
  results:
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -136.95 +/- 47.16
21
  name: mean_reward
22
  verified: false
23
  ---
24
 
25
+ # PPO Agent Playing LunarLander-v2
 
 
26
 
27
+ This is a trained model of a PPO agent playing LunarLander-v2.
28
+ To learn to code your own PPO agent and train it Unit 8 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit8
29
+
30
+ # Hyperparameters
31
+ ```python
32
+ {'exp_name': 'ppo'
33
+ 'seed': 1
34
+ 'torch_deterministic': True
35
+ 'cuda': True
36
+ 'track': False
37
+ 'wandb_project_name': 'cleanRL'
38
+ 'wandb_entity': None
39
+ 'capture_video': False
40
+ 'env_id': 'LunarLander-v2'
41
+ 'total_timesteps': 50000
42
+ 'learning_rate': 0.00025
43
+ 'num_envs': 4
44
+ 'num_steps': 128
45
+ 'anneal_lr': True
46
+ 'gae': True
47
+ 'gamma': 0.99
48
+ 'gae_lambda': 0.95
49
+ 'num_minibatches': 4
50
+ 'update_epochs': 4
51
+ 'norm_adv': True
52
+ 'clip_coef': 0.2
53
+ 'clip_vloss': True
54
+ 'ent_coef': 0.01
55
+ 'vf_coef': 0.5
56
+ 'max_grad_norm': 0.5
57
+ 'target_kl': None
58
+ 'repo_id': 'Terence3927/ppo-LunarLander-v2'
59
+ 'batch_size': 512
60
+ 'minibatch_size': 128}
61
+ ```
62
+
logs/events.out.tfevents.1668323160.terence-rl-2-0.193313.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edc25a6d2fdcecc1a43aae668eec3f34f786b0e852f8293efc3432c1f08fdc7
3
+ size 114002
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46e0ece9ed77848113298f329454e38828d1fe9cc513a731765a180c24d4b8c
3
+ size 42689
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 68.5390582682422, "std_reward": 89.22116245958337, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-09T14:45:31.053166"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -136.94549286252953, "std_reward": 47.16218198864937, "n_evaluation_episodes": 10, "eval_datetime": "2022-11-13T07:06:54.836599"}