paper-with-me

Papers

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

2021-03-08 · Gabriele Farina, Tuomas Sandholm

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.

📄 PDF Abstract BibTeX arXiv:2103.04539

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualDecision MakingSequential Decision Making

Similar Papers 제목 키워드 기반

Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity

2024-04-10 · Vahid Balazadeh, Keertana Chidambaram, Viet Nguyen, Rahul G. Krishnan 외

We study the problem of online sequential decision-making given auxiliary demonstrations from experts who made their decisions based on unobserved contextual information. These demonstrations can be viewed as solving rel…

Decision MakingMeta Reinforcement LearningMulti-Armed Banditsreinforcement-learning+3

Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering

2026-03-19 · Zhan Gao, Bishwadeep Das, Elvin Isufi arxiv

Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latt…

Multi-agent Reinforcement LearningGraph Neural NetworkDecision Making

Online Sequential Decision-Making with Unknown Delays

2024-02-12 · Ping Wu, Heyan Huang, Zhengyang Liu

In the field of online sequential decision-making, we address the problem with delays utilizing the framework of online convex optimization (OCO), where the feedback of a decision can arrive with an unknown delay. Unlike…

Decision MakingSequential Decision Making

Sequential Monte Carlo Bandits

2018-08-08 · Iñigo Urteaga, Chris H. Wiggins

We extend Bayesian multi-armed bandit (MAB) algorithms beyond their original setting by making use of sequential Monte Carlo (SMC) methods. A MAB is a sequential decision making problem where the goal is to learn a polic…

Decision MakingSequential Decision MakingThompson Sampling

Online Learning with Probing for Sequential User-Centric Selection

2025-07-27 · Tianyi Xu, Yiting Chen, Henger Li, Zheyong Bian 외 arxiv

We formalize sequential decision-making with information acquisition as the probing-augmented user-centric selection (PUCS) framework, where a learner first probes a subset of arms to obtain side information on resources…