PPO from scratch LunarLander (Deep RL Unit 8)

80f9014 verified 11 days ago

524 Bytes

tags:
  - LunarLander-v2
  - deep-rl-course
  - reinforcement-learning
  - ppo
  - custom-implementation
  - deep-reinforcement-learning
model-index:
  - name: ppo-CleanRL-LunarLander
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v2
          type: LunarLander-v2
        metrics:
          - type: mean_reward
            value: 51.05 +/- 98.11
            name: mean_reward
            verified: false

PPO (from scratch) agent for LunarLander-v2

Mean reward: 51.05 +/- 98.11