README.md

metadata

library_name: cleanrl
tags:
  - LunarLander-v2
  - ppo
  - cleanrl
  - deep-reinforcement-learning
  - reinforcement-learning
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: 268.00 +/- 15.0
            name: mean_reward

PPO Agent playing LunarLander-v2

This is a comprehensive PPO implementation checkpoint matching the complete cleanrl pipeline output layout.