README.md

metadata

library_name: stable-baselines3
tags:
  - HumanoidStandup-v2
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: PPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: HumanoidStandup-v2
          type: HumanoidStandup-v2
        metrics:
          - type: mean_reward
            value: 65822.31 +/- 10972.33
            name: mean_reward
            verified: false

PPO Agent playing HumanoidStandup-v2

This is a trained model of a PPO agent playing HumanoidStandup-v2 using the stable-baselines3 library.