Multi-armed bandits based on a variant of simulated annealing

DOI10.1007/S13226-016-0184-5zbMATH Open1351.90161OpenAlexW2475275076MaRDI QIDQ2520136FDOQ2520136

Authors: Mohammed Shahid Abdulla, Shalabh Bhatnagar 

Publication date: 13 December 2016

Published in: Indian Journal of Pure \& Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s13226-016-0184-5

Recommendations

• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem
• scientific article; zbMATH DE number 3976142
• Thompson sampling: an asymptotically optimal finite-time analysis
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem

zbMATH Keywords

statisticsapplied probabilitystochastic processesdiscrete optimization

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Cites Work

• Stochastic approximation. A dynamical systems viewpoint.
• The Nonstochastic Multiarmed Bandit Problem
• Finite-time analysis of the multiarmed bandit problem
• Adaptive game playing using multiplicative weights
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• An Adaptive Sampling Algorithm for Solving Markov Decision Processes
• The Irrevocable Multiarmed Bandit Problem
• An Asymptotically Efficient Simulation-Based Algorithm for Finite Horizon Stochastic Dynamic Programming

This page was built for publication: Multi-armed bandits based on a variant of simulated annealing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2520136)