paper-with-me

Papers

Berk-Nash Rationalizability

2025-05-27 · Ignacio Esponda, Demian Pouzo

Misspecified learning -- where agents rely on simplified or biased models -- offers a unifying framework for analyzing behavioral biases, cognitive constraints, and systematic misperceptions. We introduce Berk--Nash rationalizability, a new solution concept for such settings that parallels rationalizability in games. Our main result shows that, with probability one, every limit action -- any action played or approached infinitely often -- is Berk--Nash rationalizable. This holds regardless of whether behavior converges and offers a tractable way to bound long-run behavior without solving complex learning dynamics. We illustrate this advantage with a known example and identify general classes of environments where the rationalizable set can be easily characterized.

📄 PDF Abstract BibTeX arXiv:2505.20708

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Uncoupled Bandit Learning towards Rationalizability: Benchmarks, Barriers, and Algorithms

2021-11-10 · Jibang Wu, Haifeng Xu, Fan Yao

Under the uncoupled learning setup, the last-iterate convergence guarantee towards Nash equilibrium is shown to be impossible in many games. This work studies the last-iterate convergence guarantee in general games towar…

Decision Making

Interim correlated rationalizability in large games

2025-06-23 · Lukasz Balbus, Michael Greinecker, Kevin Reffett, Lukasz Wozny

We provide general theoretical foundations for modeling strategic uncertainty in large distributional Bayesian games with general type spaces, using a version of interim correlated rationalizability. We then focus on the…

On Existence of Berk-Nash Equilibria in Misspecified Markov Decision Processes with Infinite Spaces

2022-06-16 · Robert M. Anderson, Haosui Duanmu, Aniruddha Ghosh, M. Ali Khan

Model misspecification is a critical issue in many areas of theoretical and empirical economics. In the specific context of misspecified Markov Decision Processes, Esponda and Pouzo (2021) defined the notion of Berk-Nash…

Berk-Nash Equilibrium: A Framework for Modeling Agents with Misspecified Models

2019-11-21

We develop an equilibrium framework that relaxes the standard assumption that people have a correctly-specified view of their environment. Each player is characterized by a (possibly misspecified) subjective model, which…

Epistemic Traps: Rational Misalignment Driven by Model Misspecification

2026-01-27 · Xingcheng Xu, Jingjing Qu, Qiaosheng Zhang, Chaochao Lu 외 arxiv

The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception tha…

Reinforcement Learning