Hugging Face's logo

LeonardoMdSA
/
Pixelcopter-PLE-v0

Reinforcement Learning
Pixelcopter-PLE-v0
reinforce
custom-implementation
deep-rl-class
Eval Results (legacy)
Model card Files
xet
Community
LeonardoMdSA commited on
Commit
f8dcb5a
·
verified ·
1 Parent(s): 368f3c8

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. hyperparameters.json +1 -1
  2. results.json +3 -3
  3. video.mp4 +0 -0
hyperparameters.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "h_size": 128,
3
- "n_training_episodes": 10000,
4
  "n_evaluation_episodes": 10,
5
  "max_t": 10000,
6
  "gamma": 0.99,
 
1
  {
2
  "h_size": 128,
3
+ "n_training_episodes": 100000,
4
  "n_evaluation_episodes": 10,
5
  "max_t": 10000,
6
  "gamma": 0.99,
results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "env_id": "Pixelcopter-PLE-v0",
3
- "mean_reward": 2.6,
4
- "std_reward": 1.624807680927192,
5
  "n_evaluation_episodes": 10,
6
- "eval_datetime": "2026-01-02T22:53:02.004848"
7
  }
 
1
  {
2
  "env_id": "Pixelcopter-PLE-v0",
3
+ "mean_reward": 2.5,
4
+ "std_reward": 1.746424919657298,
5
  "n_evaluation_episodes": 10,
6
+ "eval_datetime": "2026-01-02T22:57:04.454904"
7
  }
video.mp4 CHANGED
Binary files a/video.mp4 and b/video.mp4 differ