OpenAI Gym
Nav
  • Home
  • Environments
  • Documentation
  • Forum
  • Close
  • Sign in with GitHub
LunarLander-v2

algorithm on LunarLander-v2

  • Writeup
  • 2017-01-29 22:29:21.324255
CodeReclaimers

Learning performance

Solved after 5910 episodes. Best 100-episode average reward was 209.13 ± 6.00. (LunarLander-v2 is considered "solved" when the agent obtains an average reward of at least 200 over 100 consecutive episodes.)

5910
Episodes to solve
6012
Total episodes
Solved
22m
Time to solve
Download
Tweet
How to reproduce
Comments

Comment on GitHub

Comment on GitHub

  • Environments
  • Documentation
  • Forum
  • Credits
OpenAI