README.md

metadata

model-index:
  - name: PPO LunarLander-v2
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: '-132.23 +/- 107.40'
            name: mean_reward
            verified: false

PPO Agent for LunarLander-v2

Mean reward: -132.23 ± 107.40