Planning and Acting in Partially Observable Stochastic Domains Export

@techreport{citeulike:238243, abstract = {In this paper, we bring techniques from operations research to bear on the problem of choosing optimal actions in partially observable stochastic domains. We begin by introducing the theory of Markov decision processes (mdps) and partially observable mdps (pomdps). We then outline a novel algorithm for solving pomdps off line and show how, in some cases, a finite-memory controller can be extracted from the solution to a pomdp. We conclude with a discussion of how our approach relates to...}, author = {Kaelbling, Leslie P. and Littman, Michael L. and Cassandra, Anthony R.}, citeulike-article-id = {238243}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.2141}, keywords = {markov, pomdp}, number = {CS-96-08}, posted-at = {2005-06-26 19:03:30}, priority = {3}, title = {Planning and Acting in Partially Observable Stochastic Domains}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.2141}, year = {1996} }

TY - RPRT ID - citeulike:238243 L3 - citeulike-article-id:238243 N2 - In this paper, we bring techniques from operations research to bear on the problem of choosing optimal actions in partially observable stochastic domains. We begin by introducing the theory of Markov decision processes (mdps) and partially observable mdps (pomdps). We then outline a novel algorithm for solving pomdps off line and show how, in some cases, a finite-memory controller can be extracted from the solution to a pomdp. We conclude with a discussion of how our approach relates to... IS - CS-96-08 TI - Planning and Acting in Partially Observable Stochastic Domains KW - markov KW - pomdp AU - Kaelbling, Leslie AU - Littman, Michael AU - Cassandra, Anthony PY - 1996/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.2141 ER -