A probabilistic analysis of bias optimality in unichain Markovdecision processes |
| |
Authors: | Lewis M.E. Puterman M.L. |
| |
Affiliation: | Dept. of Ind. & Oper. Eng., Michigan Univ., Ann Arbor, MI; |
| |
Abstract: | Focuses on bias optimality in unichain, finite state, and action-space Markov decision processes. Using relative value functions, we present methods for evaluating optimal bias, this leads to a probabilistic analysis which transforms the original reward problem into a minimum average cost problem. The result is an explanation of how and why bias implicitly discounts future rewards |
| |
Keywords: | |
|
|