Reinforcement Learning

OpenAI

Our goal is to develop a single AI agent that can flexibly apply its past experience on Universe environments to quickly master unfamiliar, difficult environments, which would be a major step towards general intelligence. There are many ways to help: giving us permission on your games, training agents across Universe tasks, (soon) integrating new games, or (soon) playing the games.

Reading

Reinforcement Learning
https://webdocs.cs.ualberta.ca/~sutton/book/the-book-2nd.html

Richard S. Sutton
and Andrew G. Barto
Second Edition, in progress
MIT Press, Cambridge, MA, 2017

Online draft New Code Solutions Course Materials

"The Arcade Learning Environment: An Evaluation Platform for General Agents":
https://www.jair.org/media/3912/live-3912-7087-jair.pdf

OpenAI Gym Beta
GREG BROCKMAN, JOHN SCHULMAN APRIL 27, 2016
https://openai.com/blog/openai-gym-beta/

Universe
OPENAI DECEMBER 05, 2016
https://openai.com/blog/universe/