Hugging Face's logo

gael1130
/
ppo-LunarLander-v2-from-scratch-1

Reinforcement Learning
TensorBoard
LunarLander-v2
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card Files Metrics Community
gael1130 commited on
Commit
c398091
•
1 Parent(s): d7567d0

Push agent to the Hub

Browse files
Files changed (23) hide show
  1. README.md +61 -0
  2. logs/events.out.tfevents.1711664612.2476b7501d6f.17067.0 +3 -0
  3. logs/events.out.tfevents.1711664626.2476b7501d6f.17067.1 +3 -0
  4. logs/events.out.tfevents.1711664639.2476b7501d6f.17067.2 +3 -0
  5. logs/events.out.tfevents.1711664653.2476b7501d6f.17067.3 +3 -0
  6. logs/events.out.tfevents.1711664666.2476b7501d6f.17067.4 +3 -0
  7. logs/events.out.tfevents.1711664679.2476b7501d6f.17067.5 +3 -0
  8. logs/events.out.tfevents.1711664691.2476b7501d6f.17067.6 +3 -0
  9. logs/events.out.tfevents.1711664704.2476b7501d6f.17067.7 +3 -0
  10. logs/events.out.tfevents.1711664717.2476b7501d6f.17067.8 +3 -0
  11. logs/events.out.tfevents.1711664730.2476b7501d6f.17067.9 +3 -0
  12. logs/events.out.tfevents.1711664743.2476b7501d6f.17067.10 +3 -0
  13. logs/events.out.tfevents.1711664756.2476b7501d6f.17067.11 +3 -0
  14. logs/events.out.tfevents.1711664768.2476b7501d6f.17067.12 +3 -0
  15. logs/events.out.tfevents.1711664781.2476b7501d6f.17067.13 +3 -0
  16. logs/events.out.tfevents.1711664794.2476b7501d6f.17067.14 +3 -0
  17. logs/events.out.tfevents.1711664806.2476b7501d6f.17067.15 +3 -0
  18. logs/events.out.tfevents.1711664819.2476b7501d6f.17067.16 +3 -0
  19. logs/events.out.tfevents.1711664832.2476b7501d6f.17067.17 +3 -0
  20. logs/events.out.tfevents.1711664844.2476b7501d6f.17067.18 +3 -0
  21. model.pt +3 -0
  22. replay.mp4 +0 -0
  23. 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: -127.11 +/- 69.15
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': 0.00025
34
+ 'seed': 1
35
+ 'total_timesteps': 10000
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': 128
43
+ 'anneal_lr': True
44
+ 'gae': True
45
+ 'gamma': 0.99
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-1'
57
+ 'capture_video': False
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
+ ```
61
+
logs/events.out.tfevents.1711664612.2476b7501d6f.17067.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed69550c4e83b938292007a51e896b3ab235341598d916b0c153577937051124
3
+ size 58206
logs/events.out.tfevents.1711664626.2476b7501d6f.17067.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974c24d415e87dbec5f3f117b39abeeacbf9a88c0d78324d31e963cdd2c14772
3
+ size 58144
logs/events.out.tfevents.1711664639.2476b7501d6f.17067.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19268673add65b5accd6e5b00541e8fa74a54003ac80a5043e43058e050d7f3e
3
+ size 57784
logs/events.out.tfevents.1711664653.2476b7501d6f.17067.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9106497b063acd8d7947e374d8f6e234a420c05cd96f5ffcaea7e71a993865c3
3
+ size 58144
logs/events.out.tfevents.1711664666.2476b7501d6f.17067.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262bf6c32ee8e9b3ebc9d5c2c78d4d8abe6ede783e50da0247e7f06c477c9b4a
3
+ size 57904
logs/events.out.tfevents.1711664679.2476b7501d6f.17067.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5e35931d9b829b4954371a0fcd7af77571608acb3bdc582f8141eac5e7b24a
3
+ size 58024
logs/events.out.tfevents.1711664691.2476b7501d6f.17067.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3603b900ef489b5b346db7c22ea1ebaf6ac8cc6fcd34d5a2cf1c2237699ec973
3
+ size 58024
logs/events.out.tfevents.1711664704.2476b7501d6f.17067.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b11ddd17feedd279e3a04fc467dcb47794f33360db467099fc66d28ee4b67e4
3
+ size 58144
logs/events.out.tfevents.1711664717.2476b7501d6f.17067.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed8faefb07603de3cc66239be7a7b1c7bc6f495186d4b7573753e25c40cac4f
3
+ size 57664
logs/events.out.tfevents.1711664730.2476b7501d6f.17067.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b29fbb5e4e7677c719666ca42f1515a8f5e0cc47a4a51bfefa8c3fab200176
3
+ size 58144
logs/events.out.tfevents.1711664743.2476b7501d6f.17067.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7591b73e66187163625a42cec7ea8ea786b6a55838a83371485a79e6400842d
3
+ size 57784
logs/events.out.tfevents.1711664756.2476b7501d6f.17067.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77efb917fb4bf7ae50d681ca4f7cfa6c633389468f11c7cc042cbf9d3e9b050
3
+ size 57784
logs/events.out.tfevents.1711664768.2476b7501d6f.17067.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f73e7bb8770298a267acd2c761945f92ded66bb69e07146d18f879439f634a
3
+ size 57904
logs/events.out.tfevents.1711664781.2476b7501d6f.17067.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cee8c6eefa4b8e489268308f8a9fe23483a9e8c7e204b0058d50fc873db719
3
+ size 57664
logs/events.out.tfevents.1711664794.2476b7501d6f.17067.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264af494063b1ba5c081fc6008b77195b712585da72e2b79da79ce608df1b665
3
+ size 57784
logs/events.out.tfevents.1711664806.2476b7501d6f.17067.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e218e8ba686414e7dd3f76e13f76f0002fbcef5374372c154e954c716cd588fe
3
+ size 57784
logs/events.out.tfevents.1711664819.2476b7501d6f.17067.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d8587aef7f02a4f17add42ca13ddd653ffd75dc9fdced33561f9742fa676e2
3
+ size 57784
logs/events.out.tfevents.1711664832.2476b7501d6f.17067.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f439723d7f1c0ecc28e33fca2ecdd278104a6f4f44ea07769cbe92d24eee44
3
+ size 57904
logs/events.out.tfevents.1711664844.2476b7501d6f.17067.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8348f371911effaeb625bae6977b9db2a43361e8679494deb13bd64168d87216
3
+ size 57544
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6593b4f534e856b56d9b317c620206cbf7841573684485b663e9d38936412f29
3
+ size 42898
replay.mp4 ADDED
Binary file (25.7 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"gym_id": "LunarLander-v2", "mean_reward": -127.10945199709303, "std_reward": 69.14663672454434, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-28T22:27:38.964753"}