Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games

TL;DR

This paper introduces a novel regret-minimization algorithm that operates effectively without requiring a known model of the decision process, enabling applications in unknown environments and adversarial settings.

Contribution

It presents the first regret-minimization algorithm with sublinear regret guarantees that does not assume knowledge of the decision space or payoffs, expanding applicability to unknown and black-box environments.

Findings

Achieves $O(T^{3/4})$ regret with high probability in unknown decision spaces

Outperforms prior algorithms lacking such guarantees in experiments

Applicable to various equilibrium and opponent modeling problems

Abstract

Regret minimization has proved to be a versatile tool for tree-form sequential decision making and extensive-form games. In large two-player zero-sum imperfect-information games, modern extensions of counterfactual regret minimization (CFR) are currently the practical state of the art for computing a Nash equilibrium. Most regret-minimization algorithms for tree-form sequential decision making, including CFR, require (i) an exact model of the player's decision nodes, observation nodes, and how they are linked, and (ii) full knowledge, at all times t, about the payoffs -- even in parts of the decision space that are not encountered at time t. Recently, there has been growing interest towards relaxing some of those restrictions and making regret minimization applicable to settings for which reinforcement learning methods have traditionally been used -- for example, those in which only black-box access to the environment is available. We give the first, to our knowledge, regret-minimization algorithm that guarantees sublinear regret with high probability even when requirement (i) -- and thus also (ii) -- is dropped. We formalize an online learning setting in which the strategy space is not known to the agent and gets revealed incrementally whenever the agent encounters new decision points. We give an efficient algorithm that achieves $O(T^{3/4})$ regret with high probability for that setting, even when the agent faces an adversarial environment. Our experiments show it significantly outperforms the prior algorithms for the problem, which do not have such guarantees. It can be used in any application for which regret minimization is useful: approximating Nash equilibrium or quantal response equilibrium, approximating coarse correlated equilibrium in multi-player games, learning a best response, learning safe opponent exploitation, and online play against an unknown opponent/environment.