A New Value Iteration method for the Average Cost Dynamic Programming Problem
From MaRDI portal
Publication:4388932
DOI10.1137/S0363012995291609zbMATH Open0909.90269OpenAlexW2103406407MaRDI QIDQ4388932FDOQ4388932
Authors: Dimitri P. Bertsekas 
Publication date: 10 May 1998
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/s0363012995291609
Recommendations
- Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion
- Value iteration for average cost Markov decision processes in Borel spaces
- Value iteration in countable state average cost Markov decision processes with unbounded costs
- The value iteration method for countable state Markov decision processes
- Value Iteration in a Class of Communicating Markov Decision Chains with the Average Cost Criterion
Programming involving graphs or networks (90C35) Dynamic programming in optimal control and differential games (49L20) Markov and semi-Markov decision processes (90C40)
Cited In (10)
- A unified approach to time-aggregated Markov decision processes
- Inertial Newton algorithms avoiding strict saddle points
- Convex relaxations for permutation problems
- Policy iteration type algorithms for recurrent state Markov decision processes
- Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm
- Model-based average reward reinforcement learning
- An empirical study of policy convergence in Markov decision process value iteration
- Valuing programs with deterministic and stochastic cycles
- Analyzing anonymity attacks through noisy channels
- Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion
This page was built for publication: A New Value Iteration method for the Average Cost Dynamic Programming Problem
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4388932)
