Quentin Cohen-Solal and Tristan Cazenave are winners in the following games: Surakarta, Hex 11, Hex 13, Hex 19, Havannah 8, Havannah 10, Othello, Amazons, Breakthrough, Canadian Draughts and Brazilian Draughts. They have entered many programs that use the same Deep Reinforcement Learning system. This system is original and stands out from Alpha Zero standard approaches in many ways, including the search algorithm and generation of training data. This is the first time that the same program wins so many gold medals! More details are explained in this paper accepted at the Workshop Reinforcence Learning in Games in AAAI this year.
Full results from the Computer Olympiad are available here.