{"id":"https://openalex.org/W2042830238","doi":"https://doi.org/10.1145/1102351.1102475","title":"Learning predictive state representations in dynamical systems without reset","display_name":"Learning predictive state representations in dynamical systems without reset","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2042830238","doi":"https://doi.org/10.1145/1102351.1102475","mag":"2042830238"},"language":"en","primary_location":{"id":"doi:10.1145/1102351.1102475","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028209325","display_name":"Britton Wolfe","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Britton Wolfe","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI","University of Michigan,Ann Arbor,MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066781741","display_name":"M. R. James","orcid":"https://orcid.org/0000-0003-2821-0133"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael R. James","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI","University of Michigan,Ann Arbor,MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103117754","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-8215-8295"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI","University of Michigan,Ann Arbor,MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028209325"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":10.0473,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98049774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"980","last_page":"987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.7720440030097961},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6062421202659607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.590847909450531},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5874927043914795},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.48641204833984375},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.45937028527259827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4045752286911011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3478609025478363},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1969999372959137},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12029972672462463},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.08409857749938965},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.0766763687133789}],"concepts":[{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.7720440030097961},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6062421202659607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.590847909450531},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5874927043914795},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.48641204833984375},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.45937028527259827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4045752286911011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3478609025478363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1969999372959137},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12029972672462463},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.08409857749938965},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0766763687133789},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1102351.1102475","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning  - ICML '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.7091","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.7091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2005/papers/124_PredictiveState_WolfeEtAl.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1540337045","https://openalex.org/W2113913482","https://openalex.org/W2123542217","https://openalex.org/W2154384352","https://openalex.org/W2158282517","https://openalex.org/W2159242091","https://openalex.org/W2166610875","https://openalex.org/W2169300227","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W350273603","https://openalex.org/W2393495588","https://openalex.org/W96259911","https://openalex.org/W2168225754","https://openalex.org/W4385608460","https://openalex.org/W2370772865","https://openalex.org/W1528611913","https://openalex.org/W2000034628","https://openalex.org/W2387487224","https://openalex.org/W4366146733"],"abstract_inverted_index":{"Predictive":[0],"state":[1],"representations":[2],"(PSRs)":[3],"are":[4],"a":[5,22,25,30,46],"recently-developed":[6],"way":[7],"to":[8],"model":[9],"discrete-time,":[10],"controlled":[11],"dynamical":[12],"systems.":[13],"We":[14,60],"present":[15,61],"and":[16,29,69],"describe":[17],"two":[18,67],"algorithms":[19,38,68],"for":[20,42,83],"learning":[21,58,84],"PSR":[23],"model:":[24],"Monte":[26],"Carlo":[27],"algorithm":[28,82],"temporal":[31],"difference":[32],"(TD)":[33],"algorithm.":[34,59],"Both":[35],"of":[36,76],"these":[37],"can":[39],"learn":[40],"models":[41],"systems":[43],"without":[44],"requiring":[45],"reset":[47],"action":[48],"as":[49],"was":[50],"needed":[51],"by":[52],"the":[53],"previously":[54],"available":[55],"general":[56],"PSR-model":[57],"empirical":[62],"results":[63],"that":[64,75],"compare":[65,71],"our":[66],"also":[70],"their":[72],"performance":[73],"with":[74],"existing":[77],"algorithms,":[78],"including":[79],"an":[80],"EM":[81],"POMDP":[85],"models.":[86]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
