A Predictive Theory of Games

TL;DR

This paper proposes a new probabilistic framework for game theory using information theory, allowing for a distribution over strategies influenced by external decision-makers' loss functions, and connects it to statistical physics.

Contribution

It introduces an information-theoretic approach to derive strategy distributions, linking game theory with statistical physics and extending it to variable player counts.

Findings

Distribution over strategies can be derived using information theory.

Predicted strategies depend on external loss functions.

Relationship between game theory and statistical physics is established.

Abstract

Conventional noncooperative game theory hypothesizes that the joint strategy of a set of players in a game must satisfy an "equilibrium concept". All other joint strategies are considered impossible; the only issue is what equilibrium concept is "correct". This hypothesis violates the desiderata underlying probability theory. Indeed, probability theory renders moot the problem of what equilibrium concept is correct - every joint strategy can arise with non-zero probability. Rather than a first-principles derivation of an equilibrium concept, game theory requires a first-principles derivation of a distribution over joint (mixed) strategies. This paper shows how information theory can provide such a distribution over joint strategies. If a scientist external to the game wants to distill such a distribution to a point prediction, that prediction should be set by decision theory, using their (!) loss function. So the predicted joint strategy - the "equilibrium concept" - varies with the external scientist's loss function. It is shown here that in many games, having a probability distribution with support restricted to Nash equilibria - as stipulated by conventional game theory - is impossible. It is also show how to: i) Derive an information-theoretic quantification of a player's degree of rationality; ii) Derive bounded rationality as a cost of computation; iii) Elaborate the close formal relationship between game theory and statistical physics; iv) Use this relationship to extend game theory to allow stochastically varying numbers of players.