metadata
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