README.md

metadata

tags:
  - PongNoFrameskip-v4
  - ppo
  - reinforcement-learning
  - stable-baselines3
  - deep-rl
  - atari
model-index:
  - name: PPO Pong
    results:
      - task:
          type: reinforcement-learning
          name: Pong
        dataset:
          name: PongNoFrameskip-v4
          type: atari
        metrics:
          - name: Mean Reward
            type: mean_reward
            value: 20.40 +/- 0.92

PPO Agent playing PongNoFrameskip-v4

This is a trained model of a PPO agent playing PongNoFrameskip-v4.

To learn to use this model and train yours, check the Deep Reinforcement Learning Course on Hugging Face.