Learning in Restless Bandits under Exogenous Global Markov Process

• URL: http://arxiv.org/abs/2112.09484v1
• Date: Fri, 17 Dec 2021 12:47:30 GMT
• Title: Learning in Restless Bandits under Exogenous Global Markov Process
• Authors: Tomer Gafni, Michal Yemini, Kobi Cohen
• Abstract summary: We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics. Under each global state, the rewards process of each arm evolves according to an unknown Markovian rule. We develop the Learning under Exogenous Markov Process (LEMP) algorithm to minimize regret.
• Score: 13.836565669337057
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 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.

Related papers

• Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting [67.1631453378926]
  Graph-Triggered Bandits is a framework to generalize rested and restless bandits. In this work, we focus on two specific types of monotonic bandits: rising, where the expected reward of an arm grows as the number of triggers increases, and rotting, where the opposite behavior occurs.
  arXiv  Detail & Related papers  (2024-09-09T18:23:07Z)
• A General Framework for Clustering and Distribution Matching with Bandit Feedback [81.50716021326194]
  We develop a general framework for clustering and distribution matching problems with bandit feedback. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding $delta$.
  arXiv  Detail & Related papers  (2024-09-08T12:19:12Z)
• Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacities [69.34646544774161]
  We formulate a new variant of multi-player multi-armed bandit (MAB) model, which captures arrival of requests to each arm and the policy of allocating requests to players. The challenge is how to design a distributed learning algorithm such that players select arms according to the optimal arm pulling profile. We design an iterative distributed algorithm, which guarantees that players can arrive at a consensus on the optimal arm pulling profile in only M rounds.
  arXiv  Detail & Related papers  (2024-08-20T13:57:00Z)
• Optimal Best Arm Identification with Fixed Confidence in Restless Bandits [66.700654953613]
  We study best arm identification in a restless multi-armed bandit setting with finitely many arms. The discrete-time data generated by each arm forms a homogeneous Markov chain taking values in a common, finite state space. It is demonstrated that tracking the long-term behavior of a certain Markov decision process and its state-action visitation proportions are the key ingredients in analyzing the converse and achievability bounds.
  arXiv  Detail & Related papers  (2023-10-20T10:04:05Z)
• Best Arm Identification in Restless Markov Multi-Armed Bandits [85.55466536537293]
  We study the problem of identifying the best arm in a multi-armed bandit environment. A decision entity wishes to find the index of the best arm as quickly as possible, subject to an upper bound error probability. We show that this policy achieves an upper bound that depends on $R$ and is monotonically non-increasing as $Rtoinfty$.
  arXiv  Detail & Related papers  (2022-03-29T04:58:04Z)
• Restless Multi-Armed Bandits under Exogenous Global Markov Process [20.58296570065978]
  We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics. Under each global state, the rewards process of each arm evolves according to an unknown Markovian rule. We develop the Learning under Exogenous Markov Process (LEMP) algorithm, that achieves a logarithmic regret order with time.
  arXiv  Detail & Related papers  (2022-02-28T10:29:42Z)
• Best Arm Identification under Additive Transfer Bandits [49.69203462561861]
  We study the setting when, despite the means being unknown, there is a known additive relationship between the source and target MAB instances. We propose and theoretically analyze an LUCB-style algorithm to identify an $epsilon$-optimal target arm with high probability.
  arXiv  Detail & Related papers  (2021-12-08T02:20:18Z)
• Ballooning Multi-Armed Bandits [12.205797997133397]
  We introduce Ballooning Multi-Armed Bandits (BL-MAB) In BL-MAB, the set of available arms grows (or balloons) over time. We show that if the best arm is equally likely to arrive at any time instant, a sublinear regret cannot be achieved.
  arXiv  Detail & Related papers  (2020-01-24T04:35:05Z)
• Blocking Bandits [33.14975454724348]
  We consider a novel multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. We show that with prior knowledge of the rewards and delays of all the arms, the problem of optimizing cumulative reward does not admit any pseudo-polynomial time algorithm. We design a UCB based algorithm which is shown to have $c log T + o(log T)$ cumulative regret against the greedy algorithm.
  arXiv  Detail & Related papers  (2019-07-27T20:42:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.