Reinforce Agent playing Pixelcopter-PLE-v0

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

Environment

  • Environment: Pixelcopter-PLE-v0
  • State space: 7
  • Action space: 2

Training

  • Training episodes: 27000
  • Hidden size: 64
  • Gamma: 0.99
  • Learning rate: 0.0001

Evaluation

  • Mean reward: 43.60
  • Standard deviation: 34.83
  • Mean - Std: 8.77

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

Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading

Evaluation results