The Open Cybernetics & Systemics Journal
2009, 3 : 5-12Published online 2009 August 25. DOI: 10.2174/1874110X00903010005
Publisher ID: TOCSJ-3-5
When Bellman's Principle Fails
Department of Mathematical Sciences, M & O Building, Peach Street, University of Liverpool, Liverpool, L69 3BX, UK.
ABSTRACT
We present several examples which show that the well known statements about Markov Decision Processes can fail if the loss function is not bounded.