{"id":"https://openalex.org/W2031727428","doi":"https://doi.org/10.1145/1160633.1160762","title":"Probabilistic policy reuse in a reinforcement learning agent","display_name":"Probabilistic policy reuse in a reinforcement learning agent","publication_year":2006,"publication_date":"2006-05-08","ids":{"openalex":"https://openalex.org/W2031727428","doi":"https://doi.org/10.1145/1160633.1160762","mag":"2031727428"},"language":"en","primary_location":{"id":"doi:10.1145/1160633.1160762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1160633.1160762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004703726","display_name":"Fernando Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3801-6801"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando Fern\u00e1ndez","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":283,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"720","last_page":"727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9846000075340271,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9818999767303467,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.86737459897995},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8563100099563599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7075682878494263},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6946826577186584},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5734617114067078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5278760194778442},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5058707594871521},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49988436698913574},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.473242849111557},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.44988563656806946},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1428663730621338},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10452872514724731},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.08785045146942139},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06916829943656921}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.86737459897995},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8563100099563599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075682878494263},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6946826577186584},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5734617114067078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5278760194778442},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5058707594871521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49988436698913574},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.473242849111557},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.44988563656806946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1428663730621338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10452872514724731},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.08785045146942139},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06916829943656921},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1160633.1160762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1160633.1160762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.62.118","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/afs/cs/user/mmv/www/papers/06aamas-policy-reuse.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.8253","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.8253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scalab.uc3m.es/~ffernand/papers/aamas06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323770","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W63429079","https://openalex.org/W100525821","https://openalex.org/W1255659923","https://openalex.org/W1486747874","https://openalex.org/W1494114146","https://openalex.org/W1504212531","https://openalex.org/W1598052524","https://openalex.org/W1853223271","https://openalex.org/W1964150045","https://openalex.org/W2014512216","https://openalex.org/W2090170171","https://openalex.org/W2097113539","https://openalex.org/W2114451917","https://openalex.org/W2121517924","https://openalex.org/W2122982548","https://openalex.org/W2126565096","https://openalex.org/W2128905965","https://openalex.org/W2165792602","https://openalex.org/W3011120880","https://openalex.org/W3012995883","https://openalex.org/W4212774754","https://openalex.org/W4250988145","https://openalex.org/W6639069747","https://openalex.org/W6676772908"],"related_works":["https://openalex.org/W2000444236","https://openalex.org/W2384475851","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2353602216","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"We":[0,58,92,135],"contribute":[1],"Policy":[2,98,118],"Reuse":[3,99,119],"as":[4,28,114],"a":[5,9,29,76,89,115,127,139,152],"technique":[6],"to":[7,69,79,88],"improve":[8],"reinforcement":[10],"learning":[11,34,102,147],"agent":[12,35],"with":[13,86],"guidance":[14],"from":[15],"past":[16,26,56,84],"learned":[17,44],"similar":[18,124],"policies.":[19,57],"Our":[20],"method":[21],"relies":[22],"on":[23],"using":[24],"the":[25,33,39,42,46,53,60,71,81,101,133,146,149],"policies":[27,85,125,131],"probabilistic":[30],"bias":[31],"where":[32],"faces":[36],"three":[37],"choices:":[38],"exploitation":[40,54],"of":[41,48,55,83,123,129,132,148,151],"ongoing":[43],"policy,":[45],"exploration":[47,67],"random":[49],"unexplored":[50],"actions,":[51],"and":[52,62,75,112],"introduce":[59],"algorithm":[61],"its":[63],"major":[64],"components:":[65],"an":[66],"strategy":[68],"include":[70],"new":[72,90],"reuse":[73],"bias,":[74],"similarity":[77,82],"function":[78],"estimate":[80],"respect":[87],"one.":[91],"provide":[93],"empirical":[94],"results":[95],"demonstrating":[96],"that":[97,107,137],"improves":[100],"performance":[103],"over":[104],"different":[105],"strategies":[106],"learn":[108],"without":[109],"reuse.":[110],"Interestingly":[111],"almost":[113],"side":[116],"effect,":[117],"also":[120],"identifies":[121],"classes":[122],"revealing":[126],"basis":[128,140],"core":[130],"domain.":[134,153],"demonstrate":[136],"such":[138],"can":[141],"be":[142],"built":[143],"incrementally,":[144],"contributing":[145],"structure":[150]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":16}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
