Adversarial Policies Beat Superhuman Go AIs
@misc{wang2023adversarial,title={Adversarial Policies Beat Professional-Level Go {AI}s},author={Tony Tong Wang and Adam Gleave and Nora Belrose and Tom Tseng and Michael D Dennis and Yawen Duan and Viktor Pogrebniak and Sergey Levine and Stuart Russell},year={2023},url={https://openreview.net/forum?id=Kyz1SaAcnd}}
January 8, 2023
Abstract
We attack the state-of-the-art Go-playing AI system, KataGo, by training adversarial policies that play against frozen KataGo victims. Our attack achieves a >99% win rate when KataGo uses no tree-search, and a >77% win rate when KataGo uses enough search to be superhuman. Notably, our adversaries do not win by learning to play Go better than KataGo -- in fact, our adversaries are easily beaten by human amateurs. Instead, our adversaries win by tricking KataGo into making serious blunders. Our results demonstrate that even superhuman AI systems may harbor surprising failure modes. Example games are available at [goattack.far.ai](goattack.far.ai).
