Downloads · 30 days
0
reinforce-Pixelcopter-PLE-v0
MikeDegany/reinforce-Pixelcopter-PLE-v0
reinforce-Pixelcopter-PLE-v0 is a reinforcement learning model from MikeDegany. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0.
Access
Public
Updated Sep 5, 2026
Repo size
4.8 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp413.9 KB · 65%
At a glance
- Task
- Reinforcement Learning
- Access
- Public
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026
- SHA
- 8bd8d39c
Model card
From the Hugging Face model README
Reinforce Agent playing Pixelcopter-PLE-v0
This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0.
Mean reward over 30 evaluation episodes: 35.73 +/- 24.51
Hyperparameters
{'h_size': 64, 'n_training_episodes': 50000, 'n_evaluation_episodes': 30, 'max_t': 10000, 'gamma': 0.99, 'lr': 0.0001, 'env_id': 'Pixelcopter-PLE-v0', 'state_space': 7, 'action_space': np.int64(2)}
- Task
- Reinforcement Learning
- Created
- Sep 5, 2026
- Updated
- Sep 5, 2026