A New Value Iteration method for the Average Cost Dynamic Programming Problem
- 1 March 1998
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Control and Optimization
- Vol. 36 (2) , 742-759
- https://doi.org/10.1137/s0363012995291609
Abstract
No abstract availableThis publication has 8 references indexed in Scilit:
- An Analysis of Stochastic Shortest Path ProblemsMathematics of Operations Research, 1991
- Solving H-horizon, stationary Markov decision problems in time proportional to log(H)Operations Research Letters, 1990
- Discrete versions of an algorithm due to VaraiyaIEEE Transactions on Automatic Control, 1979
- Optimal and suboptimal stationary controls for Markov chainsIEEE Transactions on Automatic Control, 1978
- Technical Note—Improved Conditions for Convergence in Undiscounted Markov Renewal ProgrammingOperations Research, 1977
- Iterative solution of the functional equations of undiscounted Markov renewal programmingJournal of Mathematical Analysis and Applications, 1971
- On Finding the Maximal Gain for Markov Decision ProcessesOperations Research, 1969
- Dynamic programming, Markov chains, and the method of successive approximationsJournal of Mathematical Analysis and Applications, 1963