{"id":"https://openalex.org/W1594201624","doi":null,"title":"Learning to Achieve Goals","display_name":"Learning to Achieve Goals","publication_year":1993,"publication_date":"1993-01-01","ids":{"openalex":"https://openalex.org/W1594201624","mag":"1594201624"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.51.3077","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.3077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/people/lpk/ijcai93.ps","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5012862284","display_name":"Leslie Pack Kaelbling","orcid":"https://orcid.org/0000-0001-6054-7145","observed_orcids":["https://orcid.org/0000-0001-6054-7145"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Leslie Pack Kaelbling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5012862284"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1452,"has_fulltext":false,"cited_by_count":227,"citation_normalized_percentile":{"value":0.95329316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1094","last_page":"1099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"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/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"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","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/temporal-difference-learning","display_name":"temporal difference learning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5210000276565552},{"id":"https://openalex.org/keywords/temporal-credit-assignment","display_name":"temporal credit assignment","score":0.9089999794960022},{"id":"https://openalex.org/keywords/relaxation-techniques","display_name":"relaxation techniques","score":0.890999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6369383931159973}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.51.3077","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.3077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/people/lpk/ijcai93.ps","raw_type":"text"},{"id":"mag:1594201624","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/ijcai/ijcai93.html#Kaelbling93","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7096025160","https://openalex.org/W6966998461","https://openalex.org/W7095785272","https://openalex.org/W7097810534","https://openalex.org/W7095289230","https://openalex.org/W3214001120","https://openalex.org/W1964150045","https://openalex.org/W7096915865","https://openalex.org/W1586189497","https://openalex.org/W4382237359"],"abstract_inverted_index":{"Temporal":[0],"difference":[1,28],"methods":[2],"solve":[3],"the":[4,52,83,92],"temporal":[5,27],"credit":[6],"assignment":[7],"problem":[8],"for":[9],"reinforcement":[10,17],"learning.":[11],"An":[12],"important":[13],"subproblem":[14],"of":[15,45,94],"general":[16],"learning":[18,20,96,99],"is":[19],"to":[21,37,58,82],"achieve":[22,59],"dynamic":[23],"goals.":[24,69],"Although":[25],"existing":[26],"methods,":[29],"such":[30],"as":[31],"Q":[32,98],"learning,":[33],"can":[34,79],"be":[35,80],"applied":[36,81],"this":[38,72],"problem,":[39],"they":[40],"do":[41],"not":[42],"take":[43],"advantage":[44],"its":[46],"special":[47],"structure.":[48],"This":[49],"paper":[50,73],"presents":[51],"DG-learning":[53],"algorithm,":[54],"which":[55],"learns":[56],"efficiently":[57],"dynamically":[60],"changing":[61],"goals":[62],"and":[63],"exhibits":[64],"good":[65],"knowledge":[66],"transfer":[67],"between":[68],"In":[70],"addition,":[71],"shows":[74],"how":[75],"traditional":[76],"relaxation":[77],"techniques":[78],"problem.":[84],"Finally,":[85],"experimental":[86],"results":[87],"are":[88],"given":[89],"that":[90],"demonstrate":[91],"superiority":[93],"DG":[95],"over":[97],"in":[100],"a":[101],"moderately":[102],"large,":[103],"synthetic,":[104],"non-deterministic":[105],"domain.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":37},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}