README.md

metadata

tags:
  - LunarLander-v2
  - reinforcement-learning
  - deep-rl-course
model-index:
  - name: CleanRL-PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: 275.00 +/- 18.00
            name: mean_reward

CleanRL-PPO Agent playing LunarLander-v2

This is a trained model of a CleanRL-PPO agent playing LunarLander-v2.