Learning to play Bayesian games

This paper discusses the implications of learning theory for the analysis of games with a move by Nature. One goal is to illuminate the issues that arise when modeling situations where players are learning about the distribution of Nature's move as well as learning about the opponents' strategies. A second goal is to argue that quite restrictive assumptions are necessary to justify the concept of Nash equilibrium without a common prior as a steady state of a learning process.

• Publication year

  2004

• Venue

  Games Econ. Behav.

• Publication date

  2004-02-01

• Fields of study

  Computer Science, Economics

• Identifiers
  DOI 10.1016/S0899-8256(03)00121-0
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Games with Incomplete Information Played by "Bayesian" Players, I-III: Part I. The Basic Model&

  2004cited by this paper
• Centre de Referència en Economia Analítica Barcelona Economics Working Paper Series Working Paper n o 27 Causal Assessment in Finite-Length Extensive-Form Games

  2004cited by this paper
• An experimental study of serial and average cost pricing mechanisms

  2003cited by this paper
• Causal assessment in finite extensive-form games

  2003cited by this paper
• Can You Guess the Game You re Playing ? 1

  2002cited by this paper
• An Experiment to Evaluate Bayesian Learning of Nash Equilibrium Play

  2001influential reference
• Learning under minimal information: An experiment on mutual fate control

  2001cited by this paper
• A Simple Model of Voice

  2001cited by this paper
• Rational Debate And One-Dimensional Conflict

  2000cited by this paper
• Experience‐weighted Attraction Learning in Normal Form Games

  1999cited by this paper
• Payoff Information and Self-Confirming Equilibrium

  1999cited by this paper
• Towards a Theory of Subjective Games

  1998cited by this paper
• Conjectural Equilibria and Rationalizability in a Game with Incomplete Information

  1997cited by this paper
• Rationality and knowledge in game theory

  1997cited by this paper
• Advances in Economics and Econometrics: Theory and Applications: Rationality and knowledge in game theory

  1997cited by this paper
• Advances In Economics and Econometrics: Theory And Applications: Seventh World Congress

  1997cited by this paper
• A Test of the Theory of Reference-Dependent Preferences

  1997cited by this paper
• Social Learning in Recurring Games

  1997cited by this paper
• Learning in extensive-form games I. Self-confirming equilibria

  1995cited by this paper
• Bayesian Learning in Repeated Games

  1995cited by this paper
• Rationalizable Conjectural Equilibrium: Between Nash and Rationalizability

  1994cited by this paper
• Self-confirming equilibrium

  1993cited by this paper
• Rational Learning Leads to Nash Equilibrium

  1993cited by this paper
• Steady state learning and Nash equilibrium

  1993influential reference

• SafeRAG: Secure Cloud-Based Retrieval-Augmented Generation for LLM-Empowered Voice Assistants

  2026cites this paper
• An intelligent ships navigation decision-making method based on multiple navigation intentions and Bayesian game under uncertain conditions

  2026cites this paper
• Forecasts as repeated cheap talk from an expert of unknown statistical bias

  2025cites this paper
• PrivRAG: A Privacy-Preserving Retrieval-Augmented Generation Protocol for LLM-Driven Voice Assistants

  2025cites this paper
• Safe Exploitative Play with Untrusted Type Beliefs

  2024cites this paper
• Modeling Other Players with Bayesian Beliefs for Games with Incomplete Information

  2024cites this paper
• Worst‐case equilibria in first‐price auctions

  2024cites this paper
• Assignment markets: Theory and experiments

  2024cites this paper
• Factorised Active Inference for Strategic Multi-Agent Interactions

  2024cites this paper
• Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf

  2024cites this paper
• Instant Resonance: Dual Strategy Enhances the Data Consensus Success Rate of Blockchain Threshold Signature Oracles

  2024cites this paper
• The Hard Pursuit of Optimal Vaccination Compliance in Heterogeneous Populations

  2024cites this paper
• Bayesian Learning with Forgetting: An Empirical Analysis of Automobile Insurance Policyholders

  2024cites this paper
• Rationalizable self-confirming equilibrium in static games with unawareness

  2024cites this paper
• Mental Models and Learning: The Case of Base-Rate Neglect

  2024influential citation
• Categorization in Games: A Bias-Variance Perspective∗

  2023cites this paper
• Unifying complexity science and machine learning

  2023cites this paper
• Learning and Equilibrium Refinements∗

  2022cites this paper
• Conjectures and underpricing in repeated mass disputes with heterogeneous plaintiffs

  2022cites this paper
• Simulation of Attacker Defender Interaction in a Noisy Security Game

  2022cites this paper
• LTE Downlink Scheduling: A True Bayesian Estimate Approach

  2022cites this paper
• A Defense-Attack Game under Multiple Preferences and Budget Constraints with Equilibrium

  2022cites this paper
• Auction Design with Data-Driven Misspecifications

  2021cites this paper
• Auction Design with Data-Driven Misspeci…cations

  2021cites this paper
• Information Cascades and Social Learning

  2021cites this paper
• Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

  2021cites this paper
• A MISATTRIBUTION THEORY OF DISCRIMINATION

  2020influential citation
• Common learning and cooperation in repeated games

  2020cites this paper
• Stability and Bayesian Consistency in Two-Sided Markets

  2020cites this paper
• Dynamic Evolution of Safety Regulation of the Ridesharing Industry under Social Media Participation

  2020cites this paper
• Errors in strategic reasoning

  2019cites this paper
• Preferences-dependent learning in the centipede game: The persistence of mistrust

  2019cites this paper
• Robust Multi-agent Counterfactual Prediction

  2019influential citation
• Ad Hoc Teamwork With Behavior Switching Agents

  2019cites this paper
• Predictability and Power in Legislative Bargaining

  2019cites this paper
• Learning Theory and Heterogeneous Play in a Signaling-Game Experiment

  2019cites this paper
• Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games

  2019cites this paper
• Games with incomplete information and uncertain payoff: from the perspective of uncertainty theory

  2019cites this paper
• Ambiguity attitudes and self-confirming equilibrium in sequential games

  2019cites this paper
• ST ] 2 5 M ay 2 01 9 Social Learning Equilibria *

  2019cites this paper
• Distributed Fictitious Play for Multiagent Systems in Uncertain Environments

  2018cites this paper
• Maximizing survival time in a random walk on an interval

  2018cites this paper
• Dispersed Behavior and Perceptions in Assortative Societies

  2018cites this paper
• Rationalizable partition-confirmed equilibrium with heterogeneous beliefs

  2018cites this paper
• Interval-Valued Cores and Interval-Valued Dominance Cores of Cooperative Games Endowed with Interval-Valued Payoffs

  2018cites this paper
• Rational Expectations , Stable Beliefs , and Stable Matching ∗

  2018cites this paper
• Endogenous sample selection: A laboratory study

  2018cites this paper
• Emergence and suppression of cooperation by action visibility in transparent games

  2018cites this paper
• Essays in Applied Microeconomic Theory

  2017influential citation
• Belief-free rationalizability and informational robustness

  2017cites this paper
• Conditional Retrospective Voting in Large Elections

  2017cites this paper
• Autonomous agents modelling other agents: A comprehensive survey and open problems

  2017cites this paper
• Type-Compatible Equilibria in Signalling Games

  2017cites this paper
• Inference by college admission departments

  2017cites this paper
• Learning and Type Compatibility in Signaling Games

  2017cites this paper
• Expectations, Networks, and Conventions

  2017cites this paper
• Distributed Fictitious Play for Optimal Behavior of Multi-Agent Systems with Incomplete Information

  2016cites this paper
• Extensive–form games with heterogeneous populations: solution concepts, equilibria characterization, learning dynamics

  2016cites this paper
• Adaptive Social Learning

  2016cites this paper
• Games with Incomplete Information When Players are Partially Aware of Others' Signals

  2016cites this paper
• Equilibrium in misspecified Markov decision processes

  2016cites this paper
• Incomplete-Information Models of Guilt Aversion in the Trust Game

  2016cites this paper
• Recency, Records, and Recaps

  2016cites this paper
• Economic Theory and Statistical Learning

  2016cites this paper
• Rational bidding in a procurement auction with subjective evaluations

  2016cites this paper
• Hidden Markov Bayesian Game with Application to Chinese Education Game

  2016cites this paper
• Distributed fictitious play for multi-agent systems with uncertainty

  2016cites this paper
• Games of Incomplete Information Played By Statisticians

  2016cites this paper
• Uncertainty and Disagreement in Equilibrium Models

  2015cites this paper
• Price Reaction to Information with Heterogeneous Beliefs and Wealth Effects: Underreaction, Momentum, and Reversal†

  2015cites this paper
• Rationalizable partition-confirmed equilibrium

  2015cites this paper
• Endogenous sample selection and partial naiveté : A laboratory study ∗

  2015cites this paper
• Berk-Nash Equilibrium : A Framework for Agents with Misspecified Models

  2015cites this paper
• Preprints of the Max Planck Institute for Research on Collective Goods Bonn 2015 / 3 The Expected Externality Mechanism in a Level-k Environment

  2015cites this paper
• Bayesian network games

  2015cites this paper
• Utilising policy types for effective ad hoc coordination in multiagent systems

  2015cites this paper
• Infinitely repeated games with self-control: A dual-self interpretation of the Monks Story

  2015cites this paper
• Discussion Paper Series Number 151 Contagion through Learning

  2015influential citation
• Rationalizable partition-confirmed equilibrium D rew

  2015cites this paper
• Distributed fictitious play in potential games of incomplete information

  2015cites this paper
• Belief and Truth in Hypothesised Behaviours

  2015cites this paper
• Disagreement, information and welfare

  2015cites this paper
• Preferences-Dependent Learning in the Centipede Game

  2015cites this paper
• An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types

  2015cites this paper
• A Framework for Modeling Bounded Rationality: Mis-Specified Bayesian-Markov Decision Processes

  2015cites this paper
• Epistemic Game Theory

  2015influential citation
• Informational Robustness and Solution Concepts

  2015cites this paper
• Rationalizable Partition-Confirmed Equilibrium

  2015cites this paper
• Is No News (Perceived As) Bad News? An Experimental Investigation of Information Disclosure

  2015cites this paper
• How to Boost Revenues in First-Price Auctions? The Magic of Disclosing Only Winning Bids from Past Auctions

  2015cites this paper
• Infinitely repeated games with self-control: A dual-self interpretation of the Monks Story

  2015cites this paper
• Berk-Nash Equilibrium: A Framework for Modeling Agents with Misspecified Models

  2014influential citation
• Players-Econometricians, Adverse Selection, and Equilibrium

  2014cites this paper
• Simultaneous bayesian auctions and computational complexity

  2014cites this paper
• Non-Cooperativity in Bayesian Social Learning

  2014cites this paper
• Exploring Ambiguity and Familiarity Effects in The “Earnings Game” Between Managers and Investors

  2014cites this paper
• Normal-form Games with Decentralized Rational Statisticians : Moral hazard and Adverse selection

  2014cites this paper
• An Equilibrium Framework for Modeling Bounded Rationality∗

  2014cites this paper
• The Folk Theorem in Repeated Games with Individual Learning

  2014cites this paper
• Learning a population distribution

  2014cites this paper