推理、记忆与推理时控制 颠覆级 有讲解视频
发表时间
2026-09-30
DOI
10.1038/s41586-026-11036-y

收录解读

现实决策常涉及隐藏信息,例如谈判、金融、竞争协作中不完全信息的博弈。Stratego作为大规模隐藏信息棋类,其开局隐藏配置超过10³³种,此前AI未能达到人类顶尖水平。

Ataraxos由策略-价值网络、信念网络和测试时搜索组成。信念网络利用自我博弈中的完整信息监督学习推断隐藏状态,测试时搜索从信念采样多个可能世界进行rollout,并使用磁镜像下降局部更新策略分布,实现高效决策。

Ataraxos在20局比赛中以15胜1负4平击败四届Stratego世界冠军,有效胜率85%,训练成本约8000美元,计算量比DeepNash低两个数量级。该方法还泛化至Barrage Stratego、Hanabi和dou dizhu,均取得超人类或SOTA结果。

该工作为大规模不完全信息决策提供了可复用的设计模式,但方法本质上仍是自我博弈强化学习与搜索的结合,并未引入全新的理论框架,创新程度属于颠覆性而非范式开创性。

原始摘要

Abstract Real-world decision-making generally involves hidden information, that is, information that is unknown to one agent but possessed by another. Unfortunately, the presence of large amounts of hidden information renders established reinforcement learning and search approaches ineffective. Even with multimillion-dollar industrial research efforts 1 , top-human-level play at Stratego—a board wargame with hidden information on a massive scale—has remained beyond the reach of artificial intelligence (AI). Here we introduce Ataraxos, an AI for Stratego based on general techniques that we developed for both self-play reinforcement learning and test-time search under hidden information. Ataraxos defeated the most decorated human Stratego player of all time by a large margin—achieving, to our knowledge, the first superhuman result in the game’s history—while consuming orders of magnitude less compute and data than previous efforts. Using the same techniques, we built a superhuman AI for Barrage Stratego and state-of-the-art AIs for Hanabi and dou dizhu , all with low cost and high sample efficiency. The success of this approach across adversarial, cooperative and team games establishes a design pattern for reinforcement learning and search that is effective under large amounts of hidden information, a longstanding desideratum of the field of strategic decision-making.

解读视频

相关论文

链接