Hugging Face's logo

gael1130
/
ppo-LunarLander-v2-from-scratch-2

Reinforcement Learning
TensorBoard
LunarLander-v2
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card Files
xet
Metrics Community
gael1130 commited on
Commit
98f7faf
·
verified ·
1 Parent(s): eae4f30

Push agent to the Hub

Browse files
Files changed (16) hide show
  1. README.md +61 -0
  2. logs/events.out.tfevents.1711666433.2476b7501d6f.24373.0 +3 -0
  3. logs/events.out.tfevents.1711666651.2476b7501d6f.24373.1 +3 -0
  4. logs/events.out.tfevents.1711666868.2476b7501d6f.24373.2 +3 -0
  5. logs/events.out.tfevents.1711667087.2476b7501d6f.24373.3 +3 -0
  6. logs/events.out.tfevents.1711667304.2476b7501d6f.24373.4 +3 -0
  7. logs/events.out.tfevents.1711667523.2476b7501d6f.24373.5 +3 -0
  8. logs/events.out.tfevents.1711667741.2476b7501d6f.24373.6 +3 -0
  9. logs/events.out.tfevents.1711667953.2476b7501d6f.24373.7 +3 -0
  10. logs/events.out.tfevents.1711668166.2476b7501d6f.24373.8 +3 -0
  11. logs/events.out.tfevents.1711668379.2476b7501d6f.24373.9 +3 -0
  12. logs/events.out.tfevents.1711668590.2476b7501d6f.24373.10 +3 -0
  13. logs/events.out.tfevents.1711668802.2476b7501d6f.24373.11 +3 -0
  14. model.pt +3 -0
  15. replay.mp4 +0 -0
  16. results.json +1 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: -107.19 +/- 44.42
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': 'default_experiment'
32
+ 'gym_id': 'LunarLander-v2'
33
+ 'learning_rate': 0.0003
34
+ 'seed': 1
35
+ 'total_timesteps': 50000
36
+ 'torch_deterministic': True
37
+ 'cuda': True
38
+ 'track': False
39
+ 'wandb_project_name': 'None'
40
+ 'wandb_entity': 'None'
41
+ 'num_envs': 4
42
+ 'num_steps': 1024
43
+ 'anneal_lr': True
44
+ 'gae': True
45
+ 'gamma': 0.999
46
+ 'gae_lambda': 0.95
47
+ 'num_minibatches': 4
48
+ 'update_epochs': 4
49
+ 'norm_adv': True
50
+ 'clip_coef': 0.2
51
+ 'clip_vloss': True
52
+ 'ent_coef': 0.01
53
+ 'vf_coef': 0.5
54
+ 'max_grad_norm': 0.5
55
+ 'target_kl': None
56
+ 'repo_id': 'gael1130/ppo-LunarLander-v2-from-scratch-2'
57
+ 'capture_video': False
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
+ ```
61
+
logs/events.out.tfevents.1711666433.2476b7501d6f.24373.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53445d603fb874d6f0955e4d30201f05875451a8ef597ab208ef017283b6046
3
+ size 464001
logs/events.out.tfevents.1711666651.2476b7501d6f.24373.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd1c8f656cf6be01be887a7bb4d435564df7fd29dc6e5ad1d64bb9b724ef7750
3
+ size 463936
logs/events.out.tfevents.1711666868.2476b7501d6f.24373.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242a03b2c0a7f3938e63ed6a01a19b6a9e90c916b86480a0797bb751bbd5a864
3
+ size 463696
logs/events.out.tfevents.1711667087.2476b7501d6f.24373.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dbf826a963ce8209c9c2ee3f128e420814ee2780eae18f3a9ce748284fc2e8c
3
+ size 463944
logs/events.out.tfevents.1711667304.2476b7501d6f.24373.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f956fec137d054c7248010ac907778bb3da0cebd010bf644d38077296ccf109
3
+ size 472596
logs/events.out.tfevents.1711667523.2476b7501d6f.24373.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722e1e2ba1b67d883a5901616557ad9c9f722d8d6a9c8f8780be374fa29ad608
3
+ size 472108
logs/events.out.tfevents.1711667741.2476b7501d6f.24373.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4fdccbda18ec117c971e98adf77b31775d3d159a4bbff3b81c3ef6146747596
3
+ size 472596
logs/events.out.tfevents.1711667953.2476b7501d6f.24373.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84ac33710233c1927b4834b489d25d1e3a63bb6616c33ce793cf5b138c24368
3
+ size 472352
logs/events.out.tfevents.1711668166.2476b7501d6f.24373.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9bac7e61bbaef605019a93ee982a487a8c717264b507fe5823b7015c26a695
3
+ size 472596
logs/events.out.tfevents.1711668379.2476b7501d6f.24373.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a528d969d77ab4013638e259fb8e5cf68a9a2bd93e19b9cce963104adbe9ce
3
+ size 472474
logs/events.out.tfevents.1711668590.2476b7501d6f.24373.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9510dd639ba5cb7789bf08bffed9844e10f31c8712832fcf1825e059a8d34f2
3
+ size 472474
logs/events.out.tfevents.1711668802.2476b7501d6f.24373.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c667b2f6e3f97c13b0ef90b3b81385e0d443a3a2fa2f52a98b148d84dd078e
3
+ size 472108
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea20c41ab2c55c05bc5b1ec49045b91343c468b34a7fbfad344378dc264706e
3
+ size 42898
replay.mp4 ADDED
Binary file (16.1 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gym_id": "LunarLander-v2", "mean_reward": -107.19141057147627, "std_reward": 44.41978123450986, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-28T23:37:03.268537"}