Hugging Face's logo

csabazs
/
Reinforce-PixelCopter

Reinforcement Learning
Pixelcopter-PLE-v0
reinforce
custom-implementation
deep-rl-class
Model card Files Community
csabazs commited on
Commit
77888cc
·
verified ·
1 Parent(s): 818d42f

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. hyperparameters.json +1 -1
  2. model.pt +1 -1
  3. replay.mp4 +0 -0
  4. results.json +1 -1
hyperparameters.json CHANGED
@@ -1 +1 @@
1
- {"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
 
1
+ {"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc9c6884b502af97e183645353bc65610c45a3ae36f851a6e9bd12f9f37fbb6d
3
  size 39732
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad9bdd6ab8ebdcb557a698f5e2b9369c827e4598a416891c9d8db485f43f042
3
  size 39732
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-16T20:52:55.194080"}
 
1
+ {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 65.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-16T21:47:24.402272"}