README.md

metadata

tags:
  - Pong-PLE-v0
  - reinforce
  - reinforcement-learning
  - custom-implementation
  - deep-rl-class
model-index:
  - name: Reinforce-Pong-PLE-v0
    results:
      - metrics:
          - type: mean_reward
            value: '-16.00 +/- 0.00'
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Pong-PLE-v0
          type: Pong-PLE-v0

  # 使用**Reinforce**智能体来玩**Pong-PLE-v0**
  这是一个使用**Reinforce**训练有素的模型玩**Pong-PLE-v0**.
  要学习使用这个模型并训练你的模型, 请查阅深度强化学习课程第5单元: https://github.com/huggingface/deep-rl-class/tree/main/unit5