Constrained Markov decision processes with total cost criteria: Lagrangian approach and dual linear program
From MaRDI portal
Publication:1298694
DOI10.1007/s001860050035zbMath0930.90081MaRDI QIDQ1298694
Publication date: 22 August 1999
Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s001860050035
Lagrangian approach; total cost; constrained Markov decision processes; countable state space; extra constraints; optimal mixed stationary-deterministic policies
Related Items
Dynamic policy for idling time preservation, Explicit explore, exploit, or escape \((E^4)\): near-optimal safety-constrained reinforcement learning in polynomial time, An exact iterative search algorithm for constrained Markov decision processes, A policy iteration heuristic for constrained discounted controlled Markov chains, Symmetric approximate linear programming for factored MDPs with application to constrained problems, Partially observable Markov decision process approximations for adaptive sensing, Constrained optimality for finite horizon semi-Markov decision processes in Polish spaces, Constrained discounted Markov decision processes with Borel state spaces