paper-with-me

Papers

Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits

2023-10-25 · Arnab Maiti, Ross Boczar, Kevin Jamieson, Lillian J. Ratliff

We study the sample complexity of identifying the pure strategy Nash equilibrium (PSNE) in a two-player zero-sum matrix game with noise. Formally, we are given a stochastic model where any learner can sample an entry $(i,j)$ of the input matrix $A\in[-1,1]^{n\times m}$ and observe $A_{i,j}+\eta$ where $\eta$ is a zero-mean 1-sub-Gaussian noise. The aim of the learner is to identify the PSNE of $A$, whenever it exists, with high probability while taking as few samples as possible. Zhou et al. (2017) presents an instance-dependent sample complexity lower bound that depends only on the entries in the row and column in which the PSNE lies. We design a near-optimal algorithm whose sample complexity matches the lower bound, up to log factors. The problem of identifying the PSNE also generalizes the problem of pure exploration in stochastic multi-armed bandits and dueling bandits, and our result matches the optimal bounds, up to log factors, in both the settings.

📄 PDF Abstract BibTeX arXiv:2310.16252

Code (1)

aistats2024-noisy-psne/midsearch 공식 구현 jax

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Multiplicative weights, equalizers, and P=PPAD

2016-09-28 · Ioannis Avramopoulos

We show that, by using multiplicative weights in a game-theoretic thought experiment (and an important convexity result on the composition of multiplicative weights with the relative entropy function), a symmetric bimatr…

Near Optimal Pure Exploration in Logistic Bandits

2024-10-28 · Eduardo Ochoa Rivera, Ambuj Tewari

Bandit algorithms have garnered significant attention due to their practical applications in real-world scenarios. However, beyond simple settings such as multi-arm or linear bandits, optimal algorithms remain scarce. No…

Gamification of Pure Exploration for Linear Bandits

2020-07-02 · ICML 2020 1 · Rémy Degenne, Pierre Ménard, Xuedong Shang, Michal Valko

We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist for standard multi-arm bandits, the exi…

Experimental Design

Pure Exploration and Regret Minimization in Matching Bandits

2021-07-31 · Flore Sentenac, Jialin Yi, Clément Calauzènes, Vianney Perchet 외

Finding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentially. We prove that it is possible to lev…

Non-Asymptotic Pure Exploration by Solving Games

2019-06-25 · NeurIPS 2019 12 · Rémy Degenne, Wouter M. Koolen, Pierre Ménard

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (…