OpenAI Gym
Nav
  • Home
  • Environments
  • Documentation
  • Forum
  • Close
  • Sign in with GitHub
Go9x9-v0

algorithm on Go9x9-v0

  • 2017-04-20 11:14:21.034123
hapiri

Learning performance

Best 100-episode average reward was -0.91 ± 0.03. (Go9x9-v0 does not have a specified reward threshold at which it's considered solved.)

-0.91 ± 0.03
Score
93s
Total runtime
Download
Tweet
  • Environments
  • Documentation
  • Forum
  • Credits
OpenAI