Decision Making under Imperfect Recall: Algorithms and Benchmarks

2026-02-16

AI Summary

This work addresses the challenge of decision-making under imperfect recall—where agents lack full access to historical information—by extending the Regret Matching (RM) algorithm to the domain of nonlinearly constrained optimization. It introduces the first benchmark suite for imperfect-recall decision problems, comprising 61 diverse instances. Experimental evaluation demonstrates that RM-based algorithms substantially outperform conventional first-order methods, such as projected gradient descent, on these large-scale constrained optimization tasks. In most scenarios, performance improvements reach several orders of magnitude, underscoring the efficacy and scalability of the proposed approach in handling complex decision environments with memory limitations.

Technology Category

• Search and Optimization: Non-convex Optimization
• Reasoning under Uncertainty: Stochastic Optimization
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• imperfect recall
• decision making
• game theory
• AI safety
• privacy

Innovation

• imperfect recall
• regret matching
• constrained optimization
• benchmark suite
• AI safety