AntiSquid commited on
Commit
1dbd989
1 Parent(s): a0a4d05

Push agent to the Hub

Browse files
README.md CHANGED
@@ -1,36 +1,61 @@
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:
11
- - metrics:
12
- - type: mean_reward
13
- value: 282.46 +/- 19.55
14
- name: mean_reward
15
- task:
16
  type: reinforcement-learning
17
  name: reinforcement-learning
18
  dataset:
19
  name: LunarLander-v2
20
  type: LunarLander-v2
 
 
 
 
 
21
  ---
22
 
23
- # **PPO** Agent playing **LunarLander-v2**
24
- This is a trained model of a **PPO** agent playing **LunarLander-v2**
25
- using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
26
-
27
- ## Usage (with Stable-baselines3)
28
- TODO: Add your code
29
-
30
-
31
- ```python
32
- from stable_baselines3 import ...
33
- from huggingface_sb3 import load_from_hub
34
 
35
- ...
36
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  tags:
3
  - LunarLander-v2
4
+ - ppo
5
  - deep-reinforcement-learning
6
  - reinforcement-learning
7
+ - custom-implementation
8
+ - deep-rl-course
9
  model-index:
10
  - name: PPO
11
  results:
12
+ - task:
 
 
 
 
13
  type: reinforcement-learning
14
  name: reinforcement-learning
15
  dataset:
16
  name: LunarLander-v2
17
  type: LunarLander-v2
18
+ metrics:
19
+ - type: mean_reward
20
+ value: 66.81 +/- 64.80
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
+
29
+ # Hyperparameters
30
+ ```python
31
+ {'exp_name': 'ppo'
32
+ 'seed': 1
33
+ 'torch_deterministic': True
34
+ 'cuda': True
35
+ 'track': False
36
+ 'wandb_project_name': 'cleanRL'
37
+ 'wandb_entity': None
38
+ 'capture_video': False
39
+ 'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
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': 'AntiSquid/PPO-LunarLander-v2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
+ ```
61
+
logs/events.out.tfevents.1678369332.1344fcc5fd2c.29532.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c31baabb66246c16cae17b5f211aa37b07be9bd0561409470f08eded19a8a6
3
+ size 659816
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
3
+ size 42597
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 282.45668832497824, "std_reward": 19.549892926397302, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-12T00:45:11.904791"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 66.81432751624162, "std_reward": 64.79910087452345, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T13:56:57.141695"}