README.md

metadata

tags:
  - LunarLander-v2
  - ppo
  - cleanrl
  - deep-rl-course
  - unit-8
  - reinforcement-learning
library_name: cleanrl
pipeline_tag: reinforcement-learning
model-index:
  - name: cleanrl-LunarLander-v2
    results:
      - task:
          name: reinforcement-learning
          type: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - name: mean_reward
            type: mean_reward
            value: 240.5 +/- 15.2

CleanRL PPO Agent playing LunarLander-v2

This is a trained PPO agent playing LunarLander-v2 using CleanRL for Unit 8 Part 1.

• Mean Reward: 240.5 +/- 15.2
• Result (mean - std): 225.30