在合作与竞争同时博弈中掌握零样本交互
Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
AI总结：
本文提出Albatross算法，通过建模其他智能体行为并学习平滑最佳响应Logit均衡，在同时博弈中实现与任意强度智能体的零样本合作与竞争，并在Battlesnake和Overcooked中显著优于AlphaZero及先前方法。
摘要：
自我博弈与规划的结合在序贯博弈中取得了巨大成功，例如在国际象棋和围棋中。然而，将AlphaZero等算法适配到同时博弈中提出了新的挑战。在这些博弈中，缺少关于其他智能体并发动作的信息是一个限制因素，因为它们可能选择不同的纳什均衡，或者根本没有进行最优博弈。因此，在同时博弈中与其他智能体交互时，对其行为进行建模至关重要。为此，我们提出了Albatross：用于学习有界理性智能体的AlphaZero以及基于模拟自我博弈的温度响应优化。Albatross学习一种新的均衡概念，即平滑最佳响应Logit均衡（SBRLE），该均衡能够与任意博弈强度的智能体进行合作和竞争。我们在一组合作与竞争的同时完全信息博弈上对Albatross进行了广泛评估。与AlphaZero相比，Albatross能够在竞争性博弈Battlesnake中利用弱智能体。此外，在合作性Overcooked基准测试中，它相比先前的最先进方法实现了37.6%的提升。
英文摘要：
The combination of self-play and planning has achieved great successes in sequential games, for instance in Chess and Go. However, adapting algorithms such as AlphaZero to simultaneous games poses a new challenge. In these games, missing information about concurrent actions of other agents is a limiting factor as they may select different Nash equilibria or do not play optimally at all. Thus, it is vital to model the behavior of the other agents when interacting with them in simultaneous games. To this end, we propose Albatross: AlphaZero for Learning Bounded-rational Agents and Temperature-based Response Optimization using Simulated Self-play. Albatross learns to play the novel equilibrium concept of a Smooth Best Response Logit Equilibrium (SBRLE), which enables cooperation and competition with agents of any playing strength. We perform an extensive evaluation of Albatross on a set of cooperative and competitive simultaneous perfect-information games. In contrast to AlphaZero, Albatross is able to exploit weak agents in the competitive game of Battlesnake. Additionally, it yields an improvement of 37.6% compared to previous state of the art in the cooperative Overcooked benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
