---
tags:
- ML-Agents-Pyramids
- ppo
- ml-agents
- deep-rl-course
- reinforcement-learning
library_name: ml-agents
---

# PPO Agent playing **ML-Agents-Pyramids**

This is a trained Unity ML-Agents PPO model playing **ML-Agents-Pyramids**.

## Evaluation Results

- Mean Reward: 1.85
- Target Threshold: -100.00