Optimal policies about discounted vector-valued Markovian decision programming and its algorithms
From MaRDI portal
Publication:1803359
zbMath0792.90087MaRDI QIDQ1803359
Publication date: 29 June 1993
Published in: Southeast Asian Bulletin of Mathematics (Search for Journal in Brave)
discrete time; countable state set; continuous transition probabilities; continuous uniformly bounded reward functions; countable compact action sets; discounted vector-valued Markov decision process; lexicographical optimal strategies
90C40: Markov and semi-Markov decision processes
Related Items