Show simple item record

Importance Sampling for Reinforcement Learning with Multiple Objectives

dc.date.accessioned2004-10-01T14:00:04Z
dc.date.accessioned2018-11-24T10:09:38Z
dc.date.available2004-10-01T14:00:04Z
dc.date.available2018-11-24T10:09:38Z
dc.date.issued2001-08-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/5568
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/5568
dc.description.abstractThis thesis considers three complications that arise from applying reinforcement learning to a real-world application. In the process of using reinforcement learning to build an adaptive electronic market-maker, we find the sparsity of data, the partial observability of the domain, and the multiple objectives of the agent to cause serious problems for existing reinforcement learning algorithms. We employ importance sampling (likelihood ratios) to achieve good performance in partially observable Markov decision processes with few data. Our importance sampling estimator requires no knowledge about the environment and places few restrictions on the method of collecting data. It can be used efficiently with reactive controllers, finite-state controllers, or policies with function approximation. We present theoretical analyses of the estimator and incorporate it into a reinforcement learning algorithm. Additionally, this method provides a complete return surface which can be used to balance multiple objectives dynamically. We demonstrate the need for multiple goals in a variety of applications and natural solutions based on our sampling method. The thesis concludes with example results from employing our algorithm to the domain of automated electronic market-making.en_US
dc.format.extent108 p.en_US
dc.format.extent10551422 bytes
dc.format.extent1268632 bytes
dc.language.isoen_US
dc.subjectAIen_US
dc.subjectreinforcement learningen_US
dc.subjectRLen_US
dc.subjectimportance samplingen_US
dc.subjectestimationen_US
dc.subjectmarket-makingen_US
dc.titleImportance Sampling for Reinforcement Learning with Multiple Objectivesen_US


Files in this item

FilesSizeFormatView
AITR-2001-003.pdf1.268Mbapplication/pdfView/Open
AITR-2001-003.ps10.55Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record