---
tags:
- reinforcement-learning
- stable-baselines3
- LunarLander-v2
- deep-rl-course
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: "269.79 +/- 20.99"
      name: mean_reward
---

# PPO LunarLander-v2

Deep Reinforcement Learning Course — Unit 1.

## Evaluation

Environment: `LunarLander-v2`

Mean reward: `269.79`

Standard deviation: `20.99`

Course score: `248.80`

Evaluation episodes: `20`

Training timesteps: `1,000,000`