Overcoming Incomplete Perception with Utile Distinction Memory
Lists
Only you see this
Abstract
This paper presents a method by which a reinforcement learning agent can solve the incomplete perception problem using memory. The agent uses a hidden Markov model (HMM) to represent its internal state space and creates memory capacity by splitting states of the HMM. The key idea is a test to determine when and how a state should be split: the agent only splits a state when doing so will help the agent predict utility. Thus the agent can create only as much memory as needed to perform the task at hand—not as much as would be required to model all the perceivable world. I call the technique UDM, for Utile Distinction Memory. Previous chapter in book Next chapter in book Recommended articles Citing articles (0) Copyright © 1993 Morgan Kaufmann Publishers, Inc. Published by Elsevier Inc. All rights reserved. Recommended articles A boundedness result for the direct heuristic dynamic programming Neural Networks, Volume 32, 2012, pp. 229-235 Download PDF View details Cities addressing climate change: Introducing a tripartite model for sustainable partnership Sustainable Cities and Society, Volume 1, Issue 4, 2011, pp. 227-235 Download PDF View details On Bounded-Degree Vertex Deletion parameterized by treewidth Discrete Applied Mathematics, Volume 160, Issues 1–2, 2012, pp. 53-60 Download PDF View details 1 2 Next Citing articles (0) Article Metrics Citations Citation Indexes: 45 Captures Readers: 53 View details Elsevier About ScienceDirect Remote access Shopping cart Advertise Contact and support Terms and conditions Privacy policy We use cookies to help provide and enhance our service and tailor content and ads. By continuing you agree to the use of cookies . Copyright © 2020 Elsevier B.V. or its licensors or contributors. ScienceDirect ® is a registered trademark of Elsevier B.V. ScienceDirect ® is a registered trademark of Elsevier B.V. {"abstracts":{"content":[{"$$":[{"$":{"id":"cesectitle1"},"#name":"section-title","_":"Abstract"},{"$$":[{"$":{"view":"all","id":"spara1"},"#name":"simple-para","_":"This paper presents a method by which a reinforcement learning agent can solve the incomplete perception problem using memory. The agent uses a hidden Markov model (HMM) to represent its internal state space and creates memory capacity by splitting states of the HMM. The key idea is a test to determine when and how a state should be split: the agent only splits a state when doing so will help the agent predict utility. Thus the agent can create only as much memory as needed to perform the task at hand—not as much as would be required to model all the perceivable world. I call the technique UDM, for Utile Distinction Memory."}],"$":{"view":"all","id":"abssec1"},"#name":"abstract-sec"}],"$":{"xmlns:ce":true,"view":"all","id":"abs1","class":"author"},"#name":"abstract"}],"floats":[],"footnotes":[],"attachments":[]},"accessOptions":{},"adobeTarget":{"variation":"control"},"article":{"publication-content":{"publicationCity":"San Francisco (CA)","publisherName":"Morgan Kaufmann","coverImageUrl":"https://ars.els-cdn.com/content/image/Dmorgank.gif","transactionsBlocked":"false","coverThumbnailUrl":"3-s2.0-B9781558603073-cov150h.gif","specialCoverImage":"3-s2.0-C20090277981-cov150h.gif","sourceOpenAccess":false,"publicationCoverImageUrl":"https://ars.els-cdn.com/content/image/3-s2.0-C20090277981-cov150h.gif"},"pii":"B9781558603073500319","dates":{"Available online":"27 June 2014","Revised":[],"Publication date":"1 January 1993"},"access":{"openArchive":false,"openAccess":false},"crawlerInformation":{"canCrawlPDFContent":false,"isCrawler":false},"document-references":16,"accessOptions":{"accessHeader":{"parameters":[],"key":"access_header_no_remote_access"},"outwardLinksSection":{"linkingHubUrl":"https://linkinghub.elsevier.com/retrieve/pii/B9781558603073500319?showall
BibTeX
@inproceedings{mccallum1993overcoming,
author = {Andrew McCallum},
title = {{Overcoming Incomplete Perception with Utile Distinction Memory}},
booktitle = {International Conference on Machine Learning},
year = {1993},
url = {https://openreview.net/forum?id=BJNPf3Z_-B},
}Loading related content...