Results 201 to 210 of about 2,867 (224)

Towards Q-learning the Whittle Index for Restless Bandits

2019 Australian & New Zealand Control Conference (ANZCC), 2019
We consider the multi-armed restless bandit problem (RMABP) with an infinite horizon average cost objective. Each arm of the RMABP is associated with a Markov process that operates in two modes: active and passive. At each time slot a controller needs to designate a subset of the arms to be active, of which the associated processes will evolve ...
Jing Fu 0001, Yoni Nazarathy, Sarat Babu Moka, Peter G. Taylor   +3 more
openaire   +3 more sources

Conditions for indexability of restless bandits and an algorithm to compute Whittle index

Advances in Applied Probability, 2022
AbstractRestless bandits are a class of sequential resource allocation problems concerned with allocating one or more resources among several alternative processes where the evolution of the processes depends on the resources allocated to them. Such models capture the fundamental trade-offs between exploration and exploitation.
Nima Akbarzadeh, Aditya Mahajan
openaire   +1 more source

Indexability and whittle index for restless bandit problems involving reset processes

IEEE Conference on Decision and Control and European Control Conference, 2011
We consider a class of restless multi-armed bandit (RMAB) problems, in which the active action resets the stochastic evolution of the system. We obtain the Whittle index in closed-form, showing that it induces a policy that is equivalent to the myopic policy, and that it is optimal for stochastically identical arms.
Keqin Liu, Richard Weber 0003, Qing Zhao 0001   +2 more
openaire   +1 more source

Conditions for indexability of restless bandits and an algorithm to compute whittle index – CORRIGENDUM

Advances in Applied Probability, 2023
Abstract This note corrects an error in the formula to obtain the Whittle index using the Sherman–Morrison formula in Akbarzadeh and Mahajan (2022). Also, some other minor typos are highlighted.
Nima Akbarzadeh, Aditya Mahajan
openaire   +1 more source

Restless bandits: indexability, computation of whittle index and learning

2022
Les bandits agités sont une classe de problèmes d'allocation séquentielle de ressources concernés par l'allocation d'une ou plusieurs ressources entre plusieurs processus alternatifs où l'évolution des processus est markovienne et dépend des ressources qui leur sont allouées.
openaire   +1 more source

Model-Based Learning of Whittle Index

ACM SIGMETRICS Performance Evaluation Review
Restless multi-armed bandits (RMABs) can model several resource allocation problems. To cite only a few applications, RMABs are used to solve optimization problems related to stochastic scheduling in a queue opportunistic scheduling machine maintenance [5], healthcare or recommendation systems. A RMAB is composed of N independent arms,
Joël Charles-Rebuffé, Nicolas Gast, Bruno Gaujal   +2 more
openaire   +1 more source

Optimality of myopic scheduling and whittle indexability for energy harvesting sensors

2012 46th Annual Conference on Information Sciences and Systems (CISS), 2012
Consider a single-hop wireless sensor network, where a central node (or fusion center, FC) collects data from a set of M energy harvesting (EH)-capable sensors (or nodes). In each time-slot only a subset of K ≤ M nodes can be scheduled by the FC for transmission over K orthogonal communication resources (e.g., frequencies).
Fabio Iannello, Osvaldo Simeone, Umberto Spagnolini   +2 more
openaire   +1 more source

Partially observable restless bandits with restarts: indexability and computation of Whittle index

2022 IEEE 61st Conference on Decision and Control (CDC), 2022
Nima Akbarzadeh, Aditya Mahajan
openaire   +1 more source

Whittle index based Q-learning for restless bandits with average reward

Automatica, 2022
Konstantin Avrachenkov, Vivek Borkar
exaly  

Robustness of Whittle Index Policy to Model Approximation

SSRN Electronic Journal, 2022
Amit Sinha, Aditya Mahajan
openaire   +1 more source