A set of successive approximation methods for discounted Markovian decision problems

DOI10.1007/BF01920264MaRDI QIDQ4133441zbMATH OpenWikidataFDO

Authors J. A. E. E. Van Nunen

Publication date 1976

Published in Zeitschrift für Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/BF01920264

Mathematics Subject Classification ID

Hamilton-Jacobi theories (49L99) Markov and semi-Markov decision processes (90C40)

Cites work

• A modified dynamic programming method for Markovian decision problems
• Contraction Mappings in the Theory Underlying Dynamic Programming
• Discounted Dynamic Programming
• Discounted semi-Markov decision processes: linear programming and policy iteration
• Discrete Dynamic Programming
• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• scientific article; zbMATH DE number 3333895 (Why is no real title available?)
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Linear Programming Solutions for Separable Markovian Decision Problems
• Some Bounds for Discounted Sequential Decision Processes
• Technical Note—Elimination of Suboptimal Actions in Markov Decision Problems

Cited in

(18)

• On theory and algorithms for Markov decision problems with the total reward criterion
• The method of value oriented successive approximations for the average reward Markov decision process
• Solving linear systems by methods based on a probabilistic interpretation
• Action-dependent stopping times and Markov decision process with unbounded rewards
• A successive approximation algorithm for an undiscounted Markov decision process
• Discounted Markov games: Generalized policy iteration method
• Markov programming by successive approximations with respect to weighted supremum norms
• A K-step look-ahead analysis of value iteration algorithms for Markov decision processes
• On integral generalized policy iteration for continuous-time linear quadratic regulations
• GPI-based design for partially unknown nonlinear two-player zero-sum games
• MARKOV DECISION PROCESSES
• (Approximate) iterated successive approximations algorithm for sequential decision processes
• Improved iterative computation of the expected discounted return in Markov and semi-Markov chains
• Optimization of STEOR networks via Markov renewal programming
• Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes
• The numerical exploitation of periodicity in Markov decision processes
• Refined performance estimation for the l-step lookahead policy in reinforcement learning
• Deep reinforcement learning for approximate policy iteration: convergence analysis and a post-earthquake disaster response case study

This page was built for publication: A set of successive approximation methods for discounted Markovian decision problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4133441)