musunurutanusha/MLAgents-Pyramids

ML-Agents Agent playing Pyramids

This is a trained model of a Pyramids agent using the Unity ML-Agents toolkit. Trained by musunurutanusha for Unit 5 of the Hugging Face Deep Reinforcement Learning Course.

Evaluation Results

• Mean Reward: 1.80 +/- 0.20
• Result (Mean - Std): 1.60 (Requirement: >= -100) -> PASSED

Files

• Pyramids.onnx: Trained ONNX policy
• Pyramids.nn: Unity Neural Network file
• configuration.yaml: Training configuration hyperparameters