AlphaStar achieves grandmaster level in the game of StarCraft II. Matches were played using a pro approved interface, on the full game without any restrictions
AlphaZero learns chess, shogi and Go by self-play, without human knowledge, to defeat existing world champion programs.
Science-18 (info) arXiv-17 (older)
Max Jaderberg’s For The Win agent learns by self-play, directly from raw pixels, to play Quake III Arena: Capture the Flag at human level.
Science-19 (info) arXiv-18 (older)
Greg Wayne’s Merlin combines memory and reinforcement learning to solve the DeepMind Lab, directly from raw pixels.
Joel Veness’ Meep is the first master-level chess program with an evaluation function that was learnt entirely from self-play, by bootstrapping from deep searches.
In a previous life, I was CTO for Elixir Studios and lead programmer on the PC strategy game Republic: the Revolution.