OpenAI Gym
Nav
  • Home
  • Environments
  • Documentation
  • Forum
  • Close
  • Sign in with GitHub
Qbert-ram-v0

algorithm on Qbert-ram-v0

  • 2016-05-09 11:34:23.762340
ceobillionaire

Learning performance

Best 100-episode average reward was 18057.75 ± 52.16. (Qbert-ram-v0 does not have a specified reward threshold at which it's considered solved.)

18057.75 ± 52.16
Score
76h
Total runtime
Download
Tweet
  • Environments
  • Documentation
  • Forum
  • Credits
OpenAI