(Approximate) iterated successive approximations algorithm for sequential decision processes

DOI10.1007/s10479-012-1073-xzbMath1274.90469OpenAlexW2014981566MaRDI QIDQ378751

Uriel G. Rothblum, Pelin G. Canbolat

Publication date: 12 November 2013

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

Full work available at URL: https://doi.org/10.1007/s10479-012-1073-x

zbMATH Keywords

successive approximationsMarkov decision chainsmodified policy iterationsequential decision processes

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Markov and semi-Markov decision processes (90C40)

Related Items

Discounted Markov decision processes with fuzzy costs, Q-learning and policy iteration algorithms for stochastic shortest path problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Truncated policy iteration methods
• Discounted Markov games: Generalized policy iteration method
• Block-successive approximation for a discounted Markov decision model
• Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
• Affine Structure and Invariant Policies for Dynamic Programs
• Improved iterative computation of the expected discounted return in Markov and semi-Markov chains
• Action Elimination Procedures for Modified Policy Iteration Algorithms
• A set of successive approximation methods for discounted Markovian decision problems
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Approximations of Dynamic Programs, I
• On the Convergence of Policy Iteration in Stationary Dynamic Programming
• Contraction Mappings in the Theory Underlying Dynamic Programming
• Some Bounds for Discounted Sequential Decision Processes