Avinash76812/reinforce-pixelcopter

Reinforce Agent playing Pixelcopter-PLE-v0

This is a trained REINFORCE agent playing Pixelcopter-PLE-v0.

This model was trained as part of the Hugging Face Deep Reinforcement Learning Course Unit 4.

Evaluation

• Mean reward: 7.20
• Standard deviation: 8.35
• Final score (mean - std): -1.15

Hyperparameters

• Hidden size: 64
• Training episodes: 5000
• Evaluation episodes: 10
• Maximum steps: 10000
• Gamma: 0.99
• Learning rate: 0.0001

Course: https://huggingface.co/learn/deep-rl-course/unit4/hands-on