README.md

metadata

library_name: stable-baselines3
tags:
  - CarRacing-v3
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: CarRacing-v3
          type: CarRacing-v3
        metrics:
          - type: mean_reward
            value: 816.66 +/- 64.92
            name: mean_reward
            verified: false

PPO Agent playing CarRacing-v3

This is a trained model of a PPO agent playing CarRacing-v3 using the stable-baselines3 library.