Hindsight and Sequential Rationality of Correlated Play

by   Dustin Morrill, et al.

Driven by recent successes in two-player, zero-sum game solving and playing, artificial intelligence work on games has increasingly focused on algorithms that produce equilibrium-based strategies. However, this approach has been less effective at producing competent players in general-sum games or those with more than two players than in two-player, zero-sum games. An appealing alternative is to consider adaptive algorithms that ensure strong performance in hindsight relative to what could have been achieved with modified behavior. This approach also leads to a game-theoretic analysis, but in the correlated play that arises from joint learning dynamics rather than factored agent behavior at equilibrium. We develop and advocate for this hindsight rationality framing of learning in general sequential decision-making settings. To this end, we re-examine mediated equilibrium and deviation types in extensive-form games, thereby gaining a more complete understanding and resolving past misconceptions. We present a set of examples illustrating the distinct strengths and weaknesses of each type of equilibrium in the literature, and prove that no tractable concept subsumes all others. This line of inquiry culminates in the definition of the deviation and equilibrium classes that correspond to algorithms in the counterfactual regret minimization (CFR) family, relating them to all others in the literature. Examining CFR in greater detail further leads to a new recursive definition of rationality in correlated play that extends sequential rationality in a way that naturally applies to hindsight evaluation.


No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

The existence of simple, uncoupled no-regret dynamics that converge to c...

Playing against no-regret players

In increasingly different contexts, it happens that a human player has t...

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

Two-player, constant-sum games are well studied in the literature, but t...

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games

Hindsight rationality is an approach to playing multi-agent, general-sum...

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections

Hindsight rationality is an approach to playing general-sum games that p...

Safe Subgame Resolving for Extensive Form Correlated Equilibrium

Correlated Equilibrium is a solution concept that is more general than N...

Discovery and Equilibrium in Games with Unawareness

Equilibrium notions for games with unawareness in the literature cannot ...

Please sign up or login with your details

Forgot password? Click here to reset