Narrow search
Showing 1 - 7 of 7
Cover Image
Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming
Feinberg, Eugene A.; Huang, Jefferson; Scherrer, Bruno - In: Operations research letters 42 (2014) 6/7, pp. 429-431
Persistent link: https://www.econbiz.de/10010428053
Cover Image
Non-randomized policies for constrained Markov decision processes
Chen, Richard C.; Feinberg, Eugene A. - In: Mathematical methods of operations research 66 (2007) 1, pp. 165-179
Persistent link: https://www.econbiz.de/10003526220
Cover Image
On the convergence of optimal actions for Markov decision processes and the optimality of (s, S) inventory policies
Feinberg, Eugene A.; Lewis, Mark E. - In: Naval research logistics : an international journal 65 (2018) 8, pp. 619-637
Persistent link: https://www.econbiz.de/10011969348
Cover Image
Complexity bounds for approximately solving discounted MDPs by value iterations
Feinberg, Eugene A.; He, Gaojin - In: Operations research letters 48 (2020) 5, pp. 543-548
Persistent link: https://www.econbiz.de/10012303405
Cover Image
Structure of optimal policies to periodic-review inventory models with convex costs and backorders for all values of discount factors
Feinberg, Eugene A.; Liang, Yan - In: Probability methods in business and industry in honor …, (pp. 29-45). 2022
Persistent link: https://www.econbiz.de/10013475359
Cover Image
Non-randomized policies for constrained Markov decision processes
Chen, Richard; Feinberg, Eugene - In: Computational Statistics 66 (2007) 1, pp. 165-179
This paper addresses constrained Markov decision processes, with expected discounted total cost criteria, which are controlled by non-randomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the series of finite horizon value functions to the...
Persistent link: https://www.econbiz.de/10010847733
Cover Image
Non-randomized policies for constrained Markov decision processes
Chen, Richard; Feinberg, Eugene - In: Mathematical Methods of Operations Research 66 (2007) 1, pp. 165-179
This paper addresses constrained Markov decision processes, with expected discounted total cost criteria, which are controlled by non-randomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the series of finite horizon value functions to the...
Persistent link: https://www.econbiz.de/10010950147