{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:59:59Z","timestamp":1775066399325,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T00:00:00Z","timestamp":1559865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007297","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,7]]},"DOI":"10.1145\/3320435.3320471","type":"proceedings-article","created":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T21:02:18Z","timestamp":1559941338000},"page":"176-180","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Value Driven Representation for Human-in-the-Loop Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Ramtin","family":"Keramati","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emma","family":"Brunskill","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9030"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_2_1_3_1","unstructured":"Lihong Li Thomas J Walsh and Michael L Littman. 2006. Towards a unified theory of state abstraction for MDPs.. In ISAIM . Lihong Li Thomas J Walsh and Michael L Littman. 2006. Towards a unified theory of state abstraction for MDPs.. In ISAIM ."},{"key":"e_1_3_2_1_4_1","volume-title":"Internatonal Conference on Autonomous Agents and Multi-Agent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 1077--1084","author":"Mandel Travis","year":"2014"},{"key":"e_1_3_2_1_5_1","unstructured":"Andrew McCallum. 1995. Reinforcement Learning with Selective Perception and Hidden State . Ph.D. Dissertation. Andrew McCallum. 1995. Reinforcement Learning with Selective Perception and Hidden State . Ph.D. Dissertation."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Andrew Kachites McCallum etalmbox. 1996. Learning to use selective attention and short-term memory in sequential tasks. In From animals to animats 4: proceedings of the fourth international conference on simulation of adaptive behavior Vol. 4. MIT Press 315. Andrew Kachites McCallum et almbox. 1996. Learning to use selective attention and short-term memory in sequential tasks. In From animals to animats 4: proceedings of the fourth international conference on simulation of adaptive behavior Vol. 4. MIT Press 315.","DOI":"10.7551\/mitpress\/3118.003.0039"},{"key":"e_1_3_2_1_7_1","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Todd K Moon. 1996. The expectation-maximization algorithm. IEEE Signal processing magazine Vol. 13 6 (1996) 47--60. Todd K Moon. 1996. The expectation-maximization algorithm. IEEE Signal processing magazine Vol. 13 6 (1996) 47--60.","DOI":"10.1109\/79.543975"},{"key":"e_1_3_2_1_9_1","unstructured":"Ian Osband and Benjamin Van Roy. 2014. Near-optimal reinforcement learning in factored MDPs. In Advances in Neural Information Processing Systems. 604--612. Ian Osband and Benjamin Van Roy. 2014. Near-optimal reinforcement learning in factored MDPs. In Advances in Neural Information Processing Systems. 604--612."},{"key":"e_1_3_2_1_10_1","unstructured":"Richard S Sutton and Andrew G Barto. 1998. Reinforcement learning: An introduction . Vol. 1. MIT press Cambridge. Richard S Sutton and Andrew G Barto. 1998. Reinforcement learning: An introduction . Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2016945.2016949"}],"event":{"name":"UMAP '19: 27th Conference on User Modeling, Adaptation and Personalization","location":"Larnaca Cyprus","acronym":"UMAP '19","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3320435.3320471","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3320435.3320471","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3320435.3320471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:22Z","timestamp":1750204402000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3320435.3320471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,7]]},"references-count":11,"alternative-id":["10.1145\/3320435.3320471","10.1145\/3320435"],"URL":"https:\/\/doi.org\/10.1145\/3320435.3320471","relation":{},"subject":[],"published":{"date-parts":[[2019,6,7]]},"assertion":[{"value":"2019-06-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}