Reinforce-Pixelcopter-PLE-v0

This is a trained model of a Reinforcement Learning agent for Pixelcopter-PLE-v0 using reinforce. Created for the Hugging Face Deep RL Course.

Evaluation Results

• Mean Reward: 12.00 +/- 2.00
• Target Environment: Pixelcopter-PLE-v0
• Library: reinforce
• Model Architecture: REINFORCE