---
tags:
- LunarLander-v2
- ppo
- reinforcement-learning
- custom-implementation
- deep-rl-course
- gymnasium
model_index:
- name: PPO (from scratch)
  results:
  - task:
      type: reinforcement-learning
    dataset:
      name: LunarLander-v2
      type: LunarLander-v2
    metrics:
    - type: mean_reward
      value: -14.47 +/- 68.73
---
# PPO Agent playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2 (trained from scratch).