{
  "model_name": "PPO Pyramids Agent",
  "algorithm": "PPO",
  "environment": "ML-Agents-Pyramids",
  "performance": {
    "mean_reward": 5.1,
    "std_reward": 0.85,
    "pyramids_completed": 5.0
  },
  "training": {
    "episodes": 3000,
    "framework": "PyTorch",
    "course": "Hugging Face Deep RL Course Unit 5"
  },
  "tags": [
    "ML-Agents-Pyramids",
    "ppo",
    "deep-reinforcement-learning",
    "reinforcement-learning",
    "ml-agents"
  ]
}