Narrow search
Showing 1 - 6 of 6
Cover Image
On boundedness of Q-learning iterates for stochastic shortest path problems
Yu, Huizhen; Bertsekas, Dimitri P. - In: Mathematics of operations research 38 (2013) 2, pp. 209-227
Persistent link: https://www.econbiz.de/10009751534
Cover Image
Dynamic programming : deterministic and stochastic models
Bertsekas, Dimitri P. - 1987
Persistent link: https://www.econbiz.de/10013475114
Cover Image
Epsilon-relaxation and auction methods for separable convex cost network flow problems
Bertsekas, Dimitri P. - In: Network optimization, (pp. 103-126). 1997
Persistent link: https://www.econbiz.de/10001320807
Cover Image
Stabilization of stochastic iterative methods for singular and nearly singular linear systems
Wang, Mengdi; Bertsekas, Dimitri P. - In: Mathematics of operations research 39 (2014) 1, pp. 1-30
Persistent link: https://www.econbiz.de/10010345230
Cover Image
On linear programming for constrained and unconstrained average-cost Markov decision processes with countable action spaces and strictly unbounded costs
Yu, Huizhen - In: Mathematics of operations research 47 (2022) 2, pp. 1474-1499
Persistent link: https://www.econbiz.de/10013365325
Cover Image
Relaxation methods for minimum cost ordinary and generalized network flow problems
Bertsekas, Dimitri P.; Tseng, Paul - In: Operations research 36 (1988) 1, pp. 93-114
Persistent link: https://www.econbiz.de/10003491209