Q-Learning Lagrange Policies for Multi-Action Restless Bandits

Mathematics of Operations Research, 2023

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

IEEE Transactions on Information Theory, 2013

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 exploitation epoch structure that achieves a regret with logarithmic order when arbitrary (but nontrivial) bounds on certain system parameters are known. When no knowledge about the system is available, we show that the proposed policy achieves a regret arbitrarily close to the logarithmic order. We further extend the problem to a decentralized setting where multiple distributed players share the arms without information exchange. Under both an exogenous restless model and an endogenous restless model, we show that a decentralized extension of the proposed policy preserves the logarithmic regret order as in the centralized setting. The results apply to adaptive learning in various dynamic systems and communication networks, as well as financial investment.

American Control Conference, 2006

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are N arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate K ≥ 1 arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown a priori. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a ...

IEEE Transactions on Signal Processing

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 nonidentical 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 related RMAB settings, the regret is defined as the reward loss with respect to a player that knows the dynamics of the problem, and plays at each time t the arm that maximizes the expected immediate value. The objective is to develop an arm-selection policy that minimizes the regret. To that end, we develop the Learning under Exogenous Markov Process (LEMP) algorithm. We analyze LEMP theoretically and establish a finite-sample bound on the regret. We show that LEMP achieves a logarithmic regret order with time. We further analyze LEMP numerically and present simulation results that support the theoretical findings and demonstrate that LEMP significantly outperforms alternative algorithms. T. Gafni and K. Cohen are with the School of Electrical and Computer Engineering,

ArXiv, 2011

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit proble...

We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit dependent cost. Successive samples from each population are iid random variables with unknown distribution. The objective is to have a feasible policy for deciding from which population to sample from, so as to maximize the expected sum of outcomes of n total samples or equivalently to minimize the regret due to lack on information of sample distributions, For this problem we consider the class of feasible uniformly fast (f-UF) convergent policies, that satisfy sample path wise the cost constraint. We first establish a necessary asymptotic lower bound for the rate of increase of the regret function of f-UF policies. Then we construct a class of f-UF policies and provide conditions under which they are asymptotically optimal within the class of f-UF policies, achieving this asymptotic lower bound. At the end we provide the explicit form of such policies for the case in which the unknown distributions are Normal with unknown means and known variances.

2010

We introduce the budget–limited multi–armed bandit (MAB), which captures situations where a learner’s actions are cos tly and constrained by a fixed budget that is incommensurable with the rewards earned from the bandit machine, and then describe a first algorithm for solving it. Since the learner h as a budget, the problem’s duration is finite. Consequently an optimal exploitation policy is not to pull the optimal arm re peatedly, but to pull the combination of arms that maximises the agent’s total reward within the budget. As such, the rewards forall arms must be estimated, because any of them may appear in the optimal combination. This di fference from existing MABs means that new approaches to maximising the total reward are required. To this end, we propose an ǫ–first algorithm, in which the firstǫ of the budget is used solely to learn the arms’ rewards (exploration), while the remaini ng 1− ǫ is used to maximise the received reward based on those estimates (exploitation). We d...

Proceedings of the AAAI Conference on Artificial Intelligence

In budget–limited multi–armed bandit (MAB) problems, thelearner’s actions are costly and constrained by a fixed budget.Consequently, an optimal exploitation policy may not be topull the optimal arm repeatedly, as is the case in other variantsof MAB, but rather to pull the sequence of different arms thatmaximises the agent’s total reward within the budget. Thisdifference from existing MABs means that new approachesto maximising the total reward are required. Given this, wedevelop two pulling policies, namely: (i) KUBE; and (ii)fractional KUBE. Whereas the former provides better performanceup to 40% in our experimental settings, the latteris computationally less expensive. We also prove logarithmicupper bounds for the regret of both policies, and show thatthese bounds are asymptotically optimal (i.e. they only differfrom the best possible regret by a constant factor).

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2017

We study the budgeted multi-armed bandit problem with stochastic action costs. In this problem, a player not only receives a reward but also pays a cost for an action of his/her choice. The goal of the player is to maximize the cumulative reward he/she receives before the total cost exceeds the budget. In the classical multi-armed bandit problem, a policy called KL-UCB is known to perform well. We propose KL-UCB-SC, an extension of this policy for the budgeted bandit problem. We prove that KL-UCB-SC is asymptotically optimal for the case of Bernoulli costs and rewards. To the best of our knowledge, this is the first result that shows asymptotic optimality in the study of the budgeted bandit problem. In fact, our regret upper bound is at least four times better than that of BTS, the best known upper bound for the budgeted bandit problem. Moreover, an empirical simulation we conducted shows that the performance of a tuned variant of KL-UCB-SC is comparable to that of state-of-the-art policies such as PD-BwK and BTS.