Reinforce-Pixelcopter-PLE-v0 Agent playing Pixelcopter-PLE-v0
This is a trained model of a Reinforce-Pixelcopter-PLE-v0 agent playing Pixelcopter-PLE-v0 using the reinforce library. Trained for the Hugging Face Deep Reinforcement Learning Course.
Evaluation Results
- Mean Reward: 19.60
- Std Reward: 8.51
- Score (Mean - Std): 11.09
Evaluation results
- mean_reward on Pixelcopter-PLE-v0self-reported19.60 +/- 8.51