rl-class-reinforce-pixelcopter
This is a trained Reinforcement Learning model for the Hugging Face Deep Reinforcement Learning Course (Unit 4b).
- Environment:
Pixelcopter-PLE-v0 - Library:
reinforce - Performance: Mean Reward =
18.0 +/- 2.0 - Description: Deep RL Course Unit 4 - Policy Gradient REINFORCE on Pixelcopter-PLE-v0
Evaluation results
- mean_reward on Pixelcopter-PLE-v0self-reported18.0 +/- 2.0