Saved in:
Bibliographic Details
Main Authors: Wyeth, Cole, Hutter, Marcus, Leike, Jan, Taylor, Jessica
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.16245
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908499032670208
author Wyeth, Cole
Hutter, Marcus
Leike, Jan
Taylor, Jessica
author_facet Wyeth, Cole
Hutter, Marcus
Leike, Jan
Taylor, Jessica
contents A Bayesian player acting in an infinite multi-player game learns to predict the other players' strategies if his prior assigns positive probability to their play (or contains a grain of truth). Kalai and Lehrer's classic grain of truth problem is to find a reasonably large class of strategies that contains the Bayes-optimal policies with respect to this class, allowing mutually-consistent beliefs about strategy choice that obey the rules of Bayesian inference. Only small classes are known to have a grain of truth and the literature contains several related impossibility results. In this paper we present a formal and general solution to the full grain of truth problem: we construct a class of strategies wide enough to contain all computable strategies as well as Bayes-optimal strategies for every reasonable prior over the class. When the "environment" is a known repeated stage game, we show convergence in the sense of [KL93a] and [KL93b]. When the environment is unknown, agents using Thompson sampling converge to play $\varepsilon$-Nash equilibria in arbitrary unknown computable multi-agent environments. Finally, we include an application to self-predictive policies that avoid planning. While these results use computability theory only as a conceptual tool to solve a classic game theory problem, we show that our solution can naturally be computationally approximated arbitrarily closely.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16245
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Limit-Computable Grains of Truth for Arbitrary Computable Extensive-Form (Un)Known Games
Wyeth, Cole
Hutter, Marcus
Leike, Jan
Taylor, Jessica
Computer Science and Game Theory
Machine Learning
Multiagent Systems
Theoretical Economics
A Bayesian player acting in an infinite multi-player game learns to predict the other players' strategies if his prior assigns positive probability to their play (or contains a grain of truth). Kalai and Lehrer's classic grain of truth problem is to find a reasonably large class of strategies that contains the Bayes-optimal policies with respect to this class, allowing mutually-consistent beliefs about strategy choice that obey the rules of Bayesian inference. Only small classes are known to have a grain of truth and the literature contains several related impossibility results. In this paper we present a formal and general solution to the full grain of truth problem: we construct a class of strategies wide enough to contain all computable strategies as well as Bayes-optimal strategies for every reasonable prior over the class. When the "environment" is a known repeated stage game, we show convergence in the sense of [KL93a] and [KL93b]. When the environment is unknown, agents using Thompson sampling converge to play $\varepsilon$-Nash equilibria in arbitrary unknown computable multi-agent environments. Finally, we include an application to self-predictive policies that avoid planning. While these results use computability theory only as a conceptual tool to solve a classic game theory problem, we show that our solution can naturally be computationally approximated arbitrarily closely.
title Limit-Computable Grains of Truth for Arbitrary Computable Extensive-Form (Un)Known Games
topic Computer Science and Game Theory
Machine Learning
Multiagent Systems
Theoretical Economics
url https://arxiv.org/abs/2508.16245