Sleeping experts and bandits approach to constrained Markov decision processes

DOI10.1016/j.automatica.2015.10.015zbMath1329.93154arXiv1412.4898OpenAlexW2132036095MaRDI QIDQ901196

Hyeong Soo Chang

Publication date: 23 December 2015

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1412.4898

zbMATH Keywords

Markov decision processesconstrained optimizationlearning algorithmsleeping experts and bandits

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Cites Work

• An exact iterative search algorithm for constrained Markov decision processes
• Simulation-based algorithms for Markov decision processes.
• Sample average approximation of expected value constrained stochastic programs
• Regret bounds for sleeping experts and bandits
• Non-randomized policies for constrained Markov decision processes
• Constrained Discounted Markov Decision Processes and Hamiltonian Cycles
• The Sample Average Approximation Method for Stochastic Discrete Optimization
• Approximate Dynamic Programming
• ${Q}$-Learning Algorithms for Constrained Markov Decision Processes With Randomized Monotone Policies: Application to MIMO Transmission Control
• Stochastic approximation algorithms for constrained optimization via simulation
• Simulation-Based Discrete Optimization of Stochastic Discrete Event Systems Subject to Non Closed-Form Constraints
• Stochastically Constrained Ranking and Selection via SCORE
• Probability Inequalities for Sums of Bounded Random Variables