Zobrazeno 1 - 1
of 1
pro vyhledávání: '"90C05 (Primary) 90C40 (Secondary)"'
Autor:
Disser, Yann, Mosis, Nils
We construct a family of Markov decision processes for which the policy iteration algorithm needs an exponential number of improving switches with Dantzig's rule, with Bland's rule, and with the Largest Increase pivot rule. This immediately translate
Externí odkaz:
http://arxiv.org/abs/2309.14034
