Retracing AI’s Steps: Go-Explore Algorithms Solve Trickiest Atari Games

Originally published at: https://developer.nvidia.com/blog/retracing-ais-steps-go-explore-algorithms-solve-trickiest-atari-games/

A team of Uber AI researchers has achieved record high scores and beaten previously unsolved Atari games with algorithms that remember and build off their past successes.  Highlighted this week in Nature, the Go-Explore family of algorithms to address limitations of traditional reinforcement learning algorithms, which struggle with complex games that provide sparse or deceptive…