This paper develops a Hoeffding inequality for the partial sums $\sum_{k=1}^n f (X_k)$, where $\{X_k\}_{k \in \mathbb{Z}_{> 0}}$ is an irreducible Markov chain on a finite state space $S$, and $f : S \to [a, b]$ is a real-valued function. Our bound is simple, general, since it only assumes irreducibility and finiteness of the state space, and powerful. In order to demonstrate its usefulness we provide two applications in multi-armed bandit problems. The first is about identifying an approximately best Markovian arm, while the second is concerned with regret minimization in the context of Markovian bandits.
Max Planck Institute（马克斯·普朗克研究所）；Université Laval（拉瓦尔大学）；University College London（伦敦大学学院）；University of Leoben（莱奥本大学）
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by expectations of the same functions of independent Bernoulli random variables. This lemma provides an alternative tool to Hoeffding-Azuma inequality to bound concentration of martingale values. Our second approach is based on integration of Hoeffding-Azuma inequality with PAC-Bayesian analysis. We also introduce a way to apply PAC-Bayesian analysis in situation …
We give a complete characterization of the sampling complexity of best Markovian arm identification in one-parameter Markovian bandit models. We derive instance specific nonasymptotic and asymptotic lower bounds which generalize those of the IID setting. We analyze the Track-and-Stop strategy, initially proposed for the IID setting, and we prove that asymptotically it is at most a factor of four apart from the lower bound. Our one-parameter Markovian bandit model is based on the notion of an exponential family of stochastic matrices for which we establish many useful properties. For the analys…
Learning in Markovian bandits with non-observable states and constrained decision epochs
IRIT, Université de Toulouse, CNRS, Toulouse INP（图卢兹大学IRIT实验室，法国国家科学研究中心，图卢兹国立理工学院）；Ikerbasque-UPV/EHU, University of the Basque Country（巴斯克科学与技术联盟-巴斯克大学）
Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In the regret-based formulation of Multi-armed Bandit (MAB) problems, except in rare instances, much of the literature focuses on arms with i.i.d. rewards. In this paper, we consider the problem of obtaining regret guarantees for MAB problems in which the rewards of each arm form a Markov chain which may not belong to a single parameter exponential family. To achieve a logarithmic regret in such problems is not difficult: a variation of standard Kullback-Leibler Upper Confidence Bound (KL-UCB) does the job. However, the constants obtained from such an analysis are poor for the following reason…
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；Institute of Engineering Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学工程学院）
We study learning algorithms for the classical Markovian bandit problem with discount. We explain how to adapt PSRL [24] and UCRL2 [2] to exploit the problem structure. These variants are called MB-PSRL and MB-UCRL2. While the regret bound and runtime of vanilla implementations of PSRL and UCRL2 are exponential in the number of bandits, we show that the episodic regret of MB-PSRL and MB-UCRL2 is $\tilde{O}(S\sqrt{nK})$ where $K$ is the number of episodes, $n$ is the number of bandits and $S$ is the number of states of each bandit (the exact bound in S, n and K is given in the paper). Up to a f…
We consider the classical multi-armed bandit problem with Markovian rewards. When played an arm changes its state in a Markovian fashion while it remains frozen when not played. The player receives a state-dependent reward each time it plays an arm. The number of states and the state transition probabilities of an arm are unknown to the player. The player's objective is to maximize its long-term total reward by learning the best arm over time. We show that under certain conditions on the state transition probabilities of the arms, a sample mean based index policy achieves logarithmic regret un…
MARBLE: Multi-Armed Restless Bandits in Latent Markovian Environment
Department of Computer and Systems Sciences (DSV), Stockholm University（斯德哥尔摩大学计算机与系统科学系）；Inria Sophia Antipolis（法国国家信息与自动化研究所索菲亚·安蒂波利斯研究中心）；Smartprofile（Smartprofile公司）
We consider the Lipschitz bandit optimization problem with an emphasis on practical efficiency. Although there is rich literature on regret analysis of this type of problem, e.g., [Kleinberg et al. 2008, Bubeck et al. 2011, Slivkins 2014], their proposed algorithms suffer from serious practical problems including extreme time complexity and dependence on oracle implementations. With this motivation, we propose a novel algorithm with an Upper Confidence Bound (UCB) exploration, namely Tree UCB-Hoeffding, using adaptive partitions. Our partitioning scheme is easy to implement and does not requir…
UT Austin（德克萨斯大学奥斯汀分校）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Amazon（亚马逊）
Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting. For the case of unstructured rewards, we prove matching upper and lower bounds for the problem-independent (i.e., gap-free) regret, both of which strictly improve the best known. A key observation is that the hard instances of this problem are those with small mean rewards, i.e., the small click-through rates that are most relevant in practice. Based on this, and the fact that small mean implies small variance for Bernoullis, our key technical result show…
In this paper we present a model for the hidden Markovian bandit problem with linear rewards. As opposed to current work on Markovian bandits, we do not assume that the state is known to the decision maker before making the decision. Furthermore, we assume structural side information where the decision maker knows in advance that there are two types of hidden states; one is common to all arms and evolves according to a Markovian distribution, and the other is unique to each arm and is distributed according to an i.i.d. process that is unique to each arm. We present an algorithm and regret anal…
We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle this problem we consider an adaptive allocation rule which at each stage combines the information from the sample means of all the arms, with the Kullback-Leibler upper confidence bound of a single arm which is selected in round-robin way. For rewards generated from a one-parameter exponential family of Markov chains, we provide a finite-time upper bound for the regret incurred from this adaptive allocation rule, which …
State variables are easily the most subtle dimension of sequential decision problems. This is especially true in the context of active learning problems (bandit problems") where decisions affect what we observe and learn. We describe our canonical framework that models {\it any} sequential decision problem, and present our definition of state variables that allows us to claim: Any properly modeled sequential decision problem is Markovian. We then present a novel two-agent perspective of partially observable Markov decision problems (POMDPs) that allows us to then claim: Any model of a real dec…
University of Washington（华盛顿大学）；Harvard University（哈佛大学）
We study a multi-armed bandit problem in a dynamic environment where arm rewards evolve in a correlated fashion according to a Markov chain. Different than much of the work on related problems, in our formulation a learning algorithm does not have access to either a priori information or observations of the state of the Markov chain and only observes smoothed reward feedback following time intervals we refer to as epochs. We demonstrate that existing methods such as UCB and $\varepsilon$-greedy can suffer linear regret in such an environment. Employing mixing-time bounds on Markov chains, we d…
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Microsoft Research（微软研究院）
In combinatorial causal bandits (CCB), the learning agent chooses at most $K$ variables in each round to intervene, collects feedback from the observed variables, with the goal of minimizing expected regret on the target variable $Y$. We study under the context of binary generalized linear models (BGLMs) with a succinct parametric representation of the causal models. We present the algorithm BGLM-OFU for Markovian BGLMs (i.e. no hidden variables) based on the maximum likelihood estimation method, and show that it achieves $O(\sqrt{T}\log T)$ regret, where $T$ is the time horizon. For the speci…
Harvard University（哈佛大学）；University of Virginia（弗吉尼亚大学）
We propose and study Collpasing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when an arm is played, the state is fully observed, thus "collapsing" any uncertainty, but when an arm is passive, no observation is made, thus allowing uncertainty to evolve. The goal is to keep as many arms in the "good" state as possible by planning a limited budget of actions per round. Such Collapsing Bandits are natural models for many healthcare domains in which workers must simultaneously monitor patients and deli…
Zhejiang Normal University（浙江师范大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；East China Normal University（华东师范大学）；The Shenzhen Research Institute of Big Data（深圳大数据研究院）
This paper proposes a general framework of multi-armed bandit (MAB) processes by introducing a type of restrictions on the switches among arms evolving in continuous time. The Gittins index process is constructed for any single arm subject to the restrictions on switches and then the optimality of the corresponding Gittins index rule is established. The Gittins indices defined in this paper are consistent with the ones for MAB processes in continuous time, integer time, semi-Markovian setting as well as general discrete time setting, so that the new theory covers the classical models as specia…
We introduce a framework for decentralized online learning for multi-armed bandits (MAB) with multiple cooperative players. The reward obtained by the players in each round depends on the actions taken by all the players. It's a team setting, and the objective is common. Information asymmetry is what makes the problem interesting and challenging. We consider three types of information asymmetry: action information asymmetry when the actions of the players can't be observed but the rewards received are common; reward information asymmetry when the actions of the other players are observable but…
A sensing policy for the restless multi-armed bandit problem with stationary but unknown reward distributions is proposed. The work is presented in the context of cognitive radios in which the bandit problem arises when deciding which parts of the spectrum to sense and exploit. It is shown that the proposed policy attains asymptotically logarithmic weak regret rate when the rewards are bounded independent and identically distributed or finite state Markovian. Simulation results verifying uniformly logarithmic weak regret are also presented. The proposed policy is a centrally coordinated index …
University of Florida（佛罗里达大学）；Inria（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）
This paper concerns error bounds for recursive equations subject to Markovian disturbances. Motivating examples abound within the fields of Markov chain Monte Carlo (MCMC) and Reinforcement Learning (RL), and many of these algorithms can be interpreted as special cases of stochastic approximation (SA). It is argued that it is not possible in general to obtain a Hoeffding bound on the error sequence, even when the underlying Markov chain is reversible and geometrically ergodic, such as the M/M/1 queue. This is motivation for the focus on mean square error bounds for parameter estimates. It is s…
The Non-Bayesian Restless Multi-Armed Bandit: A Case of Near-Logarithmic Strict Regret
Department of Aeronautics；Astronautics Massachusetts Institute of Technology, Cambridge, MA 02139, USA Ming Hsieh Department of Electrical Engineering University of Southern California, Los Angeles, CA 90089, USA Department of Electrical；Computer Engineering University of California, Davis, CA 95616, USA Email
We consider a class of restless multi-armed bandit (RMAB) problems with unknown arm dynamics. At each time, a player chooses an arm out of N arms to play, referred to as an active arm, and receives a random reward from a finite set of reward states. The reward state of the active arm transits according to an unknown Markovian dynamics. The reward state of passive arms (which are not chosen to play at time t) evolves according to an arbitrary unknown random process. The objective is an arm-selection policy that minimizes the regret, defined as the reward loss with respect to a player that alway…
Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Princeton University（普林斯顿大学）
We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics, where an unknown exogenous global Markov process governs the rewards distribution of each arm. Under each global state, the rewards process of each arm evolves according to an unknown Markovian rule, which is non-identical among different arms. At each time, a player chooses an arm out of $N$ arms to play, and receives a random reward from a finite set of reward states. The arms are restless, that is, their local state evolves regardless of the player's actions. Motivated by recent studies on …
Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Princeton University（普林斯顿大学）
We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics, where an unknown exogenous global Markov process governs the rewards distribution of each arm. Under each global state, the rewards process of each arm evolves according to an unknown Markovian rule, which is non-identical among different arms. At each time, a player chooses an arm out of N arms to play, and receives a random reward from a finite set of reward states. The arms are restless, that is, their local state evolves regardless of the player's actions. Motivated by recent studies on re…
We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics in which a player chooses M out of N arms to play at each time. The reward state of each arm transits according to an unknown Markovian rule when it is played and evolves according to an arbitrary unknown random process when it is passive. The performance of an arm selection policy is measured by regret, defined as the reward loss with respect to the case where the player knows which M arms are the most rewarding and always plays the M best arms. We construct a policy with an interleaving exploration and exploitat…
Adobe Research（Adobe研究院）；Technion Israel Institute of Technology（以色列理工学院）
We study the problem of determining the best intervention in a Causal Bayesian Network (CBN) specified only by its causal graph. We model this as a stochastic multi-armed bandit (MAB) problem with side-information, where the interventions correspond to the arms of the bandit instance. First, we propose a simple regret minimization algorithm that takes as input a semi-Markovian causal graph with atomic interventions and possibly unobservable variables, and achieves $\tilde{O}(\sqrt{M/T})$ expected simple regret, where $M$ is dependent on the input CBN and could be very small compared to the num…
Research School of Computer Science, ANU（澳大利亚国立大学计算机科学研究学院）；Google DeepMind（谷歌DeepMind）
The field of General Reinforcement Learning (GRL) formulates the problem of sequential decision-making from ground up. The history of interaction constitutes a "ground" state of the system, which never repeats. On the one hand, this generality allows GRL to model almost every domain possible, e.g.\ Bandits, MDPs, POMDPs, PSRs, and history-based environments. On the other hand, in general, the near-optimal policies in GRL are functions of complete history, which hinders not only learning but also planning in GRL. The usual way around for the planning part is that the agent is given a Markovian …
We consider an opportunistic spectrum access (OSA) problem where the time-varying condition of each channel (e.g., as a result of random fading or certain primary users' activities) is modeled as an arbitrary finite-state Markov chain. At each instance of time, a (secondary) user probes a channel and collects a certain reward as a function of the state of the channel (e.g., good channel condition results in higher data rate for the user). Each channel has potentially different state space and statistics, both unknown to the user, who tries to learn which one is the best as it goes and maximize…
