{"id":"https://openalex.org/W7100190873","doi":null,"title":"Speeding Up Reinforcement Learning with Behavior Transfer","display_name":"Speeding Up Reinforcement Learning with Behavior Transfer","alternate_titles":[],"publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7100190873"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.120.2171","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.120.2171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/~mtaylor/Publications/AAAI04-Symposium.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7100190873"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/behavior-transfer","display_name":"behavior transfer","score":0.8629999756813049},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8859999775886536},{"id":"https://openalex.org/keywords/training-time-reduction","display_name":"training time reduction","score":0.8019999861717224},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.625},{"id":"https://openalex.org/keywords/learning-speed","display_name":"learning speed","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7455000281333923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6730999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294999718666077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6266000270843506},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4652999937534332},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.27219998836517334}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.120.2171","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.120.2171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/~mtaylor/Publications/AAAI04-Symposium.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2126565096","https://openalex.org/W2128905965","https://openalex.org/W168011852","https://openalex.org/W1497976081","https://openalex.org/W2617354312","https://openalex.org/W3006195239","https://openalex.org/W110451278","https://openalex.org/W2534140487","https://openalex.org/W2524747780","https://openalex.org/W6959605043"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,12],"(RL)":[2],"methods":[3],"(Sutton":[4],"&":[5],"Barto":[6],"1998)":[7],"have":[8],"become":[9],"popular":[10],"machine":[11],"techniques":[13],"in":[14,32,42],"recent":[15],"years.":[16],"RL":[17],"has":[18,24,36],"had":[19],"some":[20,29],"experimental":[21,61],"successes":[22],"and":[23,71],"been":[25,38],"shown":[26],"to":[27,54,76],"exhibit":[28],"desirable":[30],"properties":[31],"theory,":[33],"but":[34],"it":[35],"often":[37],"found":[39],"very":[40],"slow":[41],"practice.":[43],"In":[44],"this":[45],"paper":[46],"we":[47],"introduce":[48],"behavior":[49,74],"transfer,":[50],"a":[51,64,84],"novel":[52],"approach":[53],"speeding":[55],"up":[56],"traditional":[57],"RL.":[58],"We":[59],"present":[60],"results":[62],"showing":[63],"learner":[65],"is":[66],"able":[67],"learn":[68],"one":[69],"task":[70],"then":[72],"use":[73],"transfer":[75],"markedly":[77],"reduce":[78],"the":[79],"total":[80],"training":[81],"time":[82],"for":[83],"more":[85],"complex":[86],"task.":[87]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7100190873","counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-27T00:00:00"}
