Geometric convergence of value-iteration in multichain Markov decision problems
From MaRDI portal
Publication:4187616
DOI10.2307/1426774zbMath0402.90097OpenAlexW2005357215MaRDI QIDQ4187616
Awi Federgruen, Paul J. Schweitzer
Publication date: 1979
Published in: Advances in Applied Probability (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.2307/1426774
Average Cost CriterionConvergence FactorExistence of a Uniform Convergence RateGeometric ConvergenceMarkov Decision ProblemsMudis CountedValue- Iteration Method
Minimax problems in mathematical programming (90C47) Rate of convergence, degree of approximation (41A25) Mathematical programming (90C99)
Related Items
Variational characterizations in Markov decision processes ⋮ Asymptotic expansions for dynamic programming recursions with general nonnegative matrices ⋮ Dual bounds on the equilibrium distribution of a finite Markov chain ⋮ Contraction mappings underlying undiscounted Markov decision problems. II ⋮ Computing transience bounds of emergency call centers: a hierarchical timed Petri net approach ⋮ A Brouwer fixed-point mapping approach to communicating Markov decision processes ⋮ A value-iteration scheme for undiscounted multichain Markov renewal programs ⋮ Nonstationary Markov decision problems with converging parameters ⋮ The method of value oriented successive approximations for the average reward Markov decision process ⋮ Convergence of iterates in nonlinear Perron-Frobenius theory ⋮ A value iteration method for undiscounted multichain Markov decision processes ⋮ Criteria for selecting the relaxation factor of the value iteration algorithm for undiscounted Markov and semi-Markov decision processes ⋮ Illustrated review of convergence conditions of the value iteration algorithm and the rolling horizon procedure for average-cost MDPs ⋮ Contraction mappings underlying undiscounted Markov decision problems ⋮ Improved iterative computation of the expected discounted return in Markov and semi-Markov chains ⋮ MARKOV DECISION PROCESSES ⋮ Piecewise Affine Dynamical Models of Petri Nets – Application to Emergency Call Centers* ⋮ Guaranteed approximation of Markov chains with applications to multiplexer engineering in ATM networks
