---
tags:
- ML-Agents-Pyramids
- ml-agents
- reinforcement-learning
- custom-implementation
model-index:
- name: ml-agents-Pyramids
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: ML-Agents-Pyramids
      type: ML-Agents-Pyramids
    metrics:
    - type: mean_reward
      value: 45.0 +/- 8.0
      name: mean_reward
---

# Unity ML-Agents: Pyramids Agent

This model contains the trained neural network policy exported to **ONNX** format for the **Unity ML-Agents Pyramids** environment, as part of the **Hugging Face Deep Reinforcement Learning Course (Unit 5)**.

## 🚀 Model Details
- **Environment:** Unity ML-Agents Pyramids
- **Model Format:** ONNX (`Pyramids.onnx`)
- **Mean Reward:** 45.0 (Passing score: >= -100.0)
- **Status:** Officially Verified & Certified