What Game Are We Playing? End-to-end Learning In Normal And Extensive Form Games

Abstract

Although recent work in AI has made great progress in solving large, zero-sum, extensive-form games, the underlying assumption in most past work is that the parameters of the game itself are known to the agents. This paper deals with the relatively under-explored but equally important "inverse" setting, where the parameters of the underlying game are not known to all agents, but must be learned through observations. We propose a differentiable, end-to-end learning framework for addressing this task. In particular, we consider a regularized version of the game, equivalent to a particular form of quantal response equilibrium, and develop 1) a primal-dual Newton method for finding such equilibrium points in both normal and extensive form games; and 2) a backpropagation method that lets us analytically compute gradients of all relevant game parameters through the solution itself. This ultimately lets us learn the game by training in an end-to-end fashion, effectively by integrating a "diff

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyling2018what

Related papers

• Large Scale Learning Of Agent Rationality In Two-player Zero-sum Games (2019)3.58
• Simple Uncoupled No-regret Learning Dynamics For Extensive-form Correlated Equilibrium (2021)6.34
• Learning A Game By Paying The Agents (2025)0.00
• Teaching An Old Dynamics New Tricks: Regularization-free Last-iterate Convergence In Zero-sum Games Via BNN Dynamics (2026)0.00
• The Learning Approach To Games (2025)0.00
• In-context Exploiter For Extensive-form Games (2024)0.00
• No-regret Learning In Games Is Turing Complete (2022)0.00
• A Unified Perspective On Deep Equilibrium Finding (2022)0.00