中文
相关论文

相关论文: $\varepsilon$-Good Action Identification in Fixed-…

200 篇论文

Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal…

机器学习 · 统计学 2017-11-07 Emilie Kaufmann , Wouter Koolen

We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample random outcomes of sequentially chosen pairs…

统计理论 · 数学 2016-02-16 Aurélien Garivier , Emilie Kaufmann , Wouter Koolen

We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree $\mathcal{T}$ and a threshold $\theta$, a player must answer whether the root node value of $\mathcal{T}$ is at least $\theta$ or not. In the given tree,…

机器学习 · 统计学 2026-02-02 Shoma Nameki , Atsuyoshi Nakamura , Junpei Komiyama , Koji Tabata

We propose EB-TC$\varepsilon$, a novel sampling rule for $\varepsilon$-best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TC$\varepsilon$ is an…

机器学习 · 统计学 2023-11-07 Marc Jourdan , Rémy Degenne , Emilie Kaufmann

We consider a multi-armed bandit setting with finitely many arms, in which each arm yields an $M$-dimensional vector reward upon selection. We assume that the reward of each dimension (a.k.a. {\em objective}) is generated independently of…

机器学习 · 计算机科学 2025-01-24 Zhirui Chen , P. N. Karthik , Yeow Meng Chee , Vincent Y. F. Tan

We analyze a tree search problem with an underlying Markov decision process, in which the goal is to identify the best action at the root that achieves the highest cumulative reward. We present a new tree policy that optimally allocates a…

系统与控制 · 电气工程与系统科学 2020-09-29 Yunchuan Li , Michael C. Fu , Jie Xu

We study the minimax sample complexity of $\varepsilon$-best arm identification in linear bandits. Given a compact action set $\mathcal{X}$ that spans $\mathbb{R}^d$ and an unknown reward vector $\theta\in\mathbb{R}^d$, the goal is to…

机器学习 · 计算机科学 2026-05-18 Arnab Maiti , Yunbei Xu , Kevin Jamieson

In this work, we consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of infinite-horizon discounted cost Markov Decision Process (MDP). While…

机器学习 · 统计学 2020-01-14 Devavrat Shah , Qiaomin Xie , Zhi Xu

We consider the question introduced by \cite{Mason2020} of identifying all the $\varepsilon$-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards. We give two lower bounds on the sample complexity of any algorithm…

机器学习 · 统计学 2022-04-07 Aymen Al Marjani , Tomáš Kocák , Aurélien Garivier

In fixed budget bandit identification, an algorithm sequentially observes samples from several distributions up to a given final time. It then answers a query about the set of distributions. A good algorithm will have a small probability of…

机器学习 · 统计学 2023-07-03 Rémy Degenne

Monte Carlo Tree Search (MCTS), most famously used in game-play artificial intelligence (e.g., the game of Go), is a well-known strategy for constructing approximate solutions to sequential decision problems. Its primary innovation is the…

最优化与控制 · 数学 2017-04-21 Daniel R. Jiang , Lina Al-Kanj , Warren B. Powell

We study the problem of the identification of m arms with largest means under a fixed error rate $\delta$ (fixed-confidence Top-m identification), for misspecified linear bandit models. This problem is motivated by practical applications,…

人工智能 · 计算机科学 2021-11-03 Clémence Réda , Andrea Tirinzoni , Rémy Degenne

We study the fixed-confidence best-arm identification problem in unimodal bandits, in which the means of the arms increase with the index of the arm up to their maximum, then decrease. We derive two lower bounds on the stopping time of any…

机器学习 · 计算机科学 2025-05-27 Riccardo Poiani , Marc Jourdan , Emilie Kaufmann , Rémy Degenne

The challenge of identifying the best feasible arm within a fixed budget has attracted considerable interest in recent years. However, a notable gap remains in the literature: the exact exponential rate at which the error probability…

机器学习 · 计算机科学 2025-06-04 Jie Bian , Vincent Y. F. Tan

Monte Carlo Tree Search is a popular method for solving decision making problems. Faster implementations allow for more simulations within the same wall clock time, directly improving search performance. To this end, we present an…

人工智能 · 计算机科学 2025-08-29 James Ragan , Fred Y. Hadaegh , Soon-Jo Chung

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

机器学习 · 计算机科学 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

A plethora of problems in AI, engineering and the sciences are naturally formalized as inference in discrete probabilistic models. Exact inference is often prohibitively expensive, as it may require evaluating the (unnormalized) target…

机器学习 · 计算机科学 2019-10-16 Lars Buesing , Nicolas Heess , Theophane Weber

The discovery of patterns that accurately discriminate one class label from another remains a challenging data mining task. Subgroup discovery (SD) is one of the frameworks that enables to elicit such interesting hypotheses from labeled…

数据结构与算法 · 计算机科学 2017-12-07 Guillaume Bosc , Jean-François Boulicaut , Chedy Raïssi , Mehdi Kaytoue

The construction of approximate replication strategies for pricing and hedging of derivative contracts in incomplete markets is a key problem of financial engineering. Recently Reinforcement Learning algorithms for hedging under realistic…

人工智能 · 计算机科学 2023-11-02 Oleg Szehr

Bayes-optimal behavior, while well-defined, is often difficult to achieve. Recent advances in the use of Monte-Carlo tree search (MCTS) have shown that it is possible to act near-optimally in Markov Decision Processes (MDPs) with very large…

人工智能 · 计算机科学 2012-02-20 John Asmuth , Michael L. Littman
‹ 上一页 1 2 3 10 下一页 ›