Functional characterization for average cost Markov decision processes with Doeblin's conditionsKURANO, M.Computers & mathematics with applications (1987). 1991, Vol 21, Num 11-12, pp 57-63, issn 0898-1221Conference Paper

Décision et planification dans l'incertainCHARPILLET, F; GARCIA, F; PERNY, Patrice et al.Revue d'intelligence artificielle. 2006, Vol 20, Num 2-3, issn 0992-499X, 304 p.Conference Proceedings

A survey of applications of Markov decision processesWHITE, D. J.The Journal of the Operational Research Society. 1993, Vol 44, Num 11, pp 1073-1096, issn 0160-5682Article

Mean, variance and probabilistic criteria in finite Markov decision processes: a reviewWHITE, D. J.Journal of optimization theory and applications. 1988, Vol 56, Num 1, pp 1-29, issn 0022-3239Article

Finite-stage reward functions having the Markov adequacy propertyPESTIEN, V; XIAOBO WANG.Stochastic processes and their applications. 1993, Vol 46, Num 1, pp 129-151, issn 0304-4149Article

Solution procedures for partially observed markov decision processesWHITE, C. C; SCHERER, W. T.Operations research. 1989, Vol 37, Num 5, pp 791-797, issn 0030-364X, 7 p.Article

Markov decision processes: discounted expected reward or average expected reward?WHITE, D. J.Journal of mathematical analysis and applications. 1993, Vol 172, Num 2, pp 375-384, issn 0022-247XArticle

Value iteration and rolling plans for Markov control processes with unbounded rewardsHERNANDEZ-LERMAZ, O; LASSERRE, J. B.Journal of mathematical analysis and applications. 1993, Vol 177, Num 1, pp 38-55, issn 0022-247XArticle

Quick Markov random field image fusionWRIGHT, W. A.SPIE proceedings series. 1998, pp 302-308, isbn 0-8194-2823-XConference Paper

On strong average optimality of Markov decision processes with unbounded costsGHOSH, M. K; MARCUS, S. I.Operations research letters. 1992, Vol 11, Num 2, pp 99-104, issn 0167-6377Article

Abstract dynamic programming models under commutativity conditionsVERDU, S; POOR, H. V.SIAM journal on control and optimization. 1987, Vol 25, Num 4, pp 990-1006, issn 0363-0129Article

Efficient learning control of Markov chains with many states and decisionsSATO, M; ABE, K; TAKEDA, H et al.Electrical engineering in Japan. 1987, Vol 107, Num 2, pp 131-138, issn 0424-7760Article

Fuzzy Markovian decision processBHATTACHARYYA, M.Fuzzy sets and systems. 1998, Vol 99, Num 3, pp 273-282, issn 0165-0114Article

Minimising a threshold probability in discounted Markov decision processesWHITE, D. J.Journal of mathematical analysis and applications. 1993, Vol 173, Num 2, pp 634-646, issn 0022-247XArticle

Solution to the risk-sensitive average optimality equation in communicating Markov decision chains with finite state space: An alternative approachCAVAZOS-CADENA, Rolando; HERNANDEZ-HERNANDEZ, Daniel.Mathematical methods of operations research (Heidelberg). 2002, Vol 56, Num 3, pp 473-479, issn 1432-2994, 7 p.Article

Some monotonicity results for partially observed Markov decision processesLOVEJOY, W. S.Operations research. 1987, Vol 35, Num 5, pp 736-743, issn 0030-364XArticle

TTree: Tree-based state generalization with temporally abstract actionsUTHER, William T. B; VELOSO, Manuela M.Adaptative agents and multi-agent systems (adaptation and multi-agent learning). Lecture notes in computer science. 2003, pp 260-290, issn 0302-9743, isbn 3-540-40068-0, 31 p.Book Chapter

Contraction mappings underlying undiscounted Markov decision problems. IISCHWEITZER, P. J.Journal of mathematical analysis and applications. 1988, Vol 132, Num 1, pp 154-170, issn 0022-247XArticle

Optimal dynamic routing in Markov queueing networkROSS, K. W.Automatica (Oxford). 1986, Vol 22, Num 3, pp 367-370, issn 0005-1098Article

Model-based online learning of POMDPsSHANI, Guy; BRAFMAN, Ronen I; SHIMONY, Solomon E et al.Lecture notes in computer science. 2005, pp 353-364, issn 0302-9743, isbn 3-540-29243-8, 1Vol, 12 p.Conference Paper

Active learning in partially observable markov decision processesJAULMES, Robin; PINEAU, Joelle; PRECUP, Doina et al.Lecture notes in computer science. 2005, pp 601-608, issn 0302-9743, isbn 3-540-29243-8, 1Vol, 8 p.Conference Paper

A planning algorithm for predictive state representationsIZADI, Masoumeh T; PRECUP, Doina.European workshop on reinforcement learning. 2003, pp 37-38, isbn 2-7261-1259-5, 2 p.Conference Paper

Mixed Markov decision processes in a semi-Markov environment with discounted criterionQIYING HU; JINLING WANG.Journal of mathematical analysis and applications. 1998, Vol 219, Num 1, pp 1-20, issn 0022-247XArticle

A new class of policies in vector-valued Markov decision processesWAKUTA, K.Journal of mathematical analysis and applications. 1996, Vol 202, Num 2, pp 623-628, issn 0022-247XArticle

Decision roll and horizon roll processes in infinite horizon discounted Markov decision processesWHITE, D. J.Management science. 1996, Vol 42, Num 1, pp 37-50, issn 0025-1909Article