Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions1-3, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems4. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general-purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks5,6. We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players.
Vinyals Oriol, Babuschkin Igor, Czarnecki Wojciech M, Mathieu Michaël, Dudzik Andrew, Chung Junyoung, Choi David H, Powell Richard, Ewalds Timo, Georgiev Petko, Oh Junhyuk, Horgan Dan, Kroiss Manuel, Danihelka Ivo, Huang Aja, Sifre Laurent, Cai Trevor, Agapiou John P, Jaderberg Max, Vezhnevets Alexander S, Leblond Rémi, Pohlen Tobias, Dalibard Valentin, Budden David, Sulsky Yury, Molloy James, Paine Tom L, Gulcehre Caglar, Wang Ziyu, Pfaff Tobias, Wu Yuhuai, Ring Roman, Yogatama Dani, Wünsch Dario, McKinney Katrina, Smith Oliver, Schaul Tom, Lillicrap Timothy, Kavukcuoglu Koray, Hassabis Demis, Apps Chris, Silver David