Hindsight rationality is an approach to playing general-sum games that
prescribes no-regret learning dynamics for individual agents with respect to a
set of deviations, and further describes jointly rational behavior among
multiple agents with mediated equilibria. To develop hindsight rational
learning in sequential decision-making settings, we formalize behavioral
deviations as a general class of deviations that respect the structure of
extensive-form games. Integrating the idea of time selection into
counterfactual regret minimization (CFR), we introduce the extensive-form
regret minimization (EFR) algorithm that achieves hindsight rationality for any
given set of behavioral deviations with computation that scales closely with
the complexity of the set. We identify behavioral deviation subsets, the
partial sequence deviation types, that subsume previously studied types and
lead to efficient EFR instances in games with moderate lengths. In addition, we
present a thorough empirical analysis of EFR instantiated with different
deviation types in benchmark games, where we find that stronger types typically
induce better performance.

该研究旨在通过在 extensive-form games 中进行 behavioral deviations 来开发一种回顾性理性的学习算法，该算法采用 counterfactual regret minimization 策略，并能适用于任意给定的行为偏差集合，通过实验表明在不同的 deviation types 中，EFR 通常表现更好。