In game theory, imperfect-recall decision problems model situations in which an agent forgets information it held before. They encompass games such as the ``absentminded driver'' and team games with limited communication. In this paper, we introduce the first benchmark suite for imperfect-recall decision problems. Our benchmarks capture a variety of problem types, including ones concerning privacy in AI systems that elicit sensitive information, and AI safety via testing of agents in simulation. Across 61 problem instances generated using this suite, we evaluate the performance of different algorithms for finding first-order optimal strategies in such problems. In particular, we introduce the family of regret matching (RM) algorithms for nonlinear constrained optimization. This class of parameter-free algorithms has enjoyed tremendous success in solving large two-player zero-sum games, but, surprisingly, they were hitherto relatively unexplored beyond that setting. Our key finding is that RM algorithms consistently outperform commonly employed first-order optimizers such as projected gradient descent, often by orders of magnitude. This establishes, for the first time, the RM family as a formidable approach to large-scale constrained optimization problems.

翻译：在博弈论中，不完全回忆决策问题模拟了智能体遗忘先前所持信息的情境。这类问题涵盖了诸如“心不在焉的司机”博弈以及有限通信的团队博弈等模型。本文首次提出了针对不完全回忆决策问题的基准测试套件。我们的基准涵盖多种问题类型，包括涉及人工智能系统在获取敏感信息时的隐私问题，以及通过模拟环境测试智能体来实现AI安全性等问题。基于该套件生成的61个问题实例，我们评估了不同算法在此类问题中寻找一阶最优策略的性能。特别地，我们引入了用于非线性约束优化的遗憾匹配（RM）算法族。这类无参数算法在求解大规模双人零和博弈中已取得巨大成功，但令人惊讶的是，此前该算法在此类场景之外的应用探索相对有限。我们的核心发现是：RM算法始终优于投影梯度下降等常用一阶优化器，且通常能实现数量级上的性能提升。这首次确立了RM算法族作为解决大规模约束优化问题的强大方法。