Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes

DOI10.1287/moor.1110.0525zbMath1243.90233OpenAlexW1991591460MaRDI QIDQ2884309

Uriel G. Rothblum, Eugene A. Feinberg

Publication date: 24 May 2012

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.1110.0525

zbMATH Keywords

Markov decision processesconstrained Markov decision processesoccupancy measuressplitting occupancy measures

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40)

Related Items (19)

Conditions for the solvability of the linear programming formulation for constrained discounted Markov decision processes ⋮ Stationary Markov Nash Equilibria for Nonzero-Sum Constrained ARAT Markov Games ⋮ Constrained continuous-time Markov decision processes on the finite horizon ⋮ Constrained optimality for finite horizon semi-Markov decision processes in Polish spaces ⋮ The multi-armed bandit, with constraints ⋮ Extreme Occupation Measures in Markov Decision Processes with an Absorbing State ⋮ Nash equilibria for total expected reward absorbing Markov games: the constrained and unconstrained cases ⋮ Absorbing Markov decision processes ⋮ A Convex Programming Approach for Discrete-Time Markov Decision Processes under the Expected Total Reward Criterion ⋮ An exact iterative search algorithm for constrained Markov decision processes ⋮ Sufficiency of Deterministic Policies for Atomless Discounted and Uniformly Absorbing MDPs with Multiple Criteria ⋮ Note on discounted continuous-time Markov decision processes with a lower bounding function ⋮ Extreme point characterization of constrained nonstationary infinite-horizon Markov decision processes with finite state space ⋮ Constrained discounted Markov decision processes with Borel state spaces ⋮ Risk-sensitive semi-Markov decision processes with general utilities and multiple criteria ⋮ Constrained Markov Decision Processes with Expected Total Reward Criteria ⋮ Optimality of Mixed Policies for Average Continuous-Time Markov Decision Processes with Constraints ⋮ Absorbing Continuous-Time Markov Decision Processes with Total Cost Criteria ⋮ On the reduction of total‐cost and average‐cost MDPs to discounted MDPs

This page was built for publication: Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes