---
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