Narrow search
Showing 1 - 10 of 18
Cover Image
Strong polynomiality of policy iterations for average-cost MDPs modeling replacement and maintenance problems
Feinberg, Eugene A.; Huang, Jefferson - In: Operations research letters 41 (2013) 3, pp. 249-251
Persistent link: https://www.econbiz.de/10009757359
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
Reduction of total-cost and average-cost MDPs with weakly continuous transition probabilities to discounted MDPs
Feinberg, Eugene A.; Huang, Jefferson - In: Operations research letters 46 (2018) 2, pp. 179-184
Persistent link: https://www.econbiz.de/10011824851
Cover Image
Constrained semi-Markov decision processes with average rewards
Feinberg, Eugene A. - In: Zeitschrift für Operations-Research : ZOR ; … 39 (1994) 3, pp. 257-288
Persistent link: https://www.econbiz.de/10001166172
Cover Image
Optimality of deterministic policies for certain stochastic control problems with multiple criteria and constraints
Feinberg, Eugene A. - In: Mathematical control theory and finance, (pp. 137-148). 2008
Persistent link: https://www.econbiz.de/10003755590
Cover Image
On essential information in sequential decision processes
Feinberg, Eugene A. - In: Mathematical methods of operations research 62 (2005) 2, pp. 399-410
Persistent link: https://www.econbiz.de/10003232691
Cover Image
Notes on equivalent stationary policies in Markov decision processes with total rewards
Feinberg, Eugene A. - In: Mathematical methods of operations research 44 (1996) 2, pp. 205-221
Persistent link: https://www.econbiz.de/10001207352
Cover Image
Variance minimization for constrained discounted continuous-time MDPs with exponentially distributed stopping times
Fei, Jun; Feinberg, Eugene A. - 2013
Persistent link: https://www.econbiz.de/10010192736
Cover Image
The multi-armed bandit, with constraints
Denardo, Eric V.; Feinberg, Eugene A.; Rothblum, Uriel G. - 2013
Persistent link: https://www.econbiz.de/10010192829
Cover Image
Splitting randomized stationary policies in total-reward Markov decision processes
Feinberg, Eugene A.; Rothblum, Uriel G. - In: Mathematics of operations research 37 (2012) 1, pp. 129-153
Persistent link: https://www.econbiz.de/10009512302