Hugging Face's logo

knight9114
/
ppo-LunarLander-v2-unit8.1

Reinforcement Learning
TensorBoard
LunarLander-v2
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results
Model card Files Metrics Community
knight9114 commited on
Commit
e65f65e
•
1 Parent(s): 18a39d0

Push agent to the Hub

Browse files
Files changed (14) hide show
  1. README.md +57 -0
  2. logs/charts_SPS/events.out.tfevents.1723805973.0ae896124e08.2165.29 +3 -0
  3. logs/charts_learning-rate/events.out.tfevents.1723805973.0ae896124e08.2165.28 +3 -0
  4. logs/events.out.tfevents.1723805972.0ae896124e08.2165.27 +3 -0
  5. logs/losses_approx-kl/events.out.tfevents.1723805973.0ae896124e08.2165.34 +3 -0
  6. logs/losses_clip-fraction/events.out.tfevents.1723805973.0ae896124e08.2165.35 +3 -0
  7. logs/losses_entropy/events.out.tfevents.1723805973.0ae896124e08.2165.32 +3 -0
  8. logs/losses_explained-variance/events.out.tfevents.1723805973.0ae896124e08.2165.36 +3 -0
  9. logs/losses_old-approx-kl/events.out.tfevents.1723805973.0ae896124e08.2165.33 +3 -0
  10. logs/losses_policy-loss/events.out.tfevents.1723805973.0ae896124e08.2165.31 +3 -0
  11. logs/losses_value-loss/events.out.tfevents.1723805973.0ae896124e08.2165.30 +3 -0
  12. model.pt +3 -0
  13. replay.mp4 +0 -0
  14. results.json +1 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: -134.81 +/- 132.27
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
+ 'raw_exp_version': None
33
+ 'n_hidden_layers': 1
34
+ 'd_hidden_layers': 64
35
+ 'env_id': 'LunarLander-v2'
36
+ 'n_envs': 4
37
+ 'total_timesteps': 1000000
38
+ 'batch_timesteps': 128
39
+ 'n_mini_batches': 4
40
+ 'n_epochs': 4
41
+ 'lr': 0.0003
42
+ 'alpha': 0.2
43
+ 'gamma': 0.99
44
+ 'lmbda': 0.95
45
+ 'normalize_advantages': True
46
+ 'coef_vf': 0.5
47
+ 'coef_s': 0.01
48
+ 'max_grad_norm': 1.0
49
+ 'seed': 2546260713
50
+ 'cuda': True
51
+ 'deterministic': True
52
+ 'repo_id': 'knight9114/ppo-LunarLander-v2-unit8.1'
53
+ 'batch_size': 512
54
+ 'mini_batch_size': 128
55
+ 'exp_version': 'version_13'}
56
+ ```
57
+
logs/charts_SPS/events.out.tfevents.1723805973.0ae896124e08.2165.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9474f1886ad9398ee78bf97c07d579af732c5ea69715e4a0041247ed5e98c6
3
+ size 89895
logs/charts_learning-rate/events.out.tfevents.1723805973.0ae896124e08.2165.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f62cea8233601ce121770d64ab8474990d6c8ff58cc19de182c7e8c575dc212
3
+ size 89895
logs/events.out.tfevents.1723805972.0ae896124e08.2165.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef461e4782e14580eb0ab733f7380902b684f2f367e538c43b2cd22d461dd25
3
+ size 442257
logs/losses_approx-kl/events.out.tfevents.1723805973.0ae896124e08.2165.34 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992a9c51ca932c44ee2c64213e8335c965957b35e8fac812096530c233c2d0ff
3
+ size 89895
logs/losses_clip-fraction/events.out.tfevents.1723805973.0ae896124e08.2165.35 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f8b88563a225e1f1926ffade5688fe3c778a4c3f383af3fd43787b3166d83a
3
+ size 89895
logs/losses_entropy/events.out.tfevents.1723805973.0ae896124e08.2165.32 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcd0b7e31276ee0eb5d4974f030091fe653fa6ef5ae01b4a5f0c0551b369fe5
3
+ size 89895
logs/losses_explained-variance/events.out.tfevents.1723805973.0ae896124e08.2165.36 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8c52efd2ef45881fdc815549d1c1fcecd87cf4f4bfa2d274d9a1fcfe5a68a3
3
+ size 89895
logs/losses_old-approx-kl/events.out.tfevents.1723805973.0ae896124e08.2165.33 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4b6c03c87d3d3b20876ddf0407a41776a40cafc4dcae4e2f16fa471f9475a4
3
+ size 89895
logs/losses_policy-loss/events.out.tfevents.1723805973.0ae896124e08.2165.31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2134b15237dfd11a880ba4eae22b4f21122da99f3bb21d9d32d801026a8a69f
3
+ size 89895
logs/losses_value-loss/events.out.tfevents.1723805973.0ae896124e08.2165.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e93f06c1dd7822d24cf568d04dfaa8d4c3f0bb25ddaa0eb9ae55c1d70486a43
3
+ size 89895
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f85102fc964930378f58e52434933666bedd9a18751c3cbaeadd5a79ed9981
3
+ size 43154
replay.mp4 ADDED
Binary file (206 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -134.81130809339462, "std_reward": 132.26597766629948, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-16T11:28:08.296289"}