{"id":"https://openalex.org/W50296447","doi":null,"title":"Programming robots using reinforcement learning and teaching","display_name":"Programming robots using reinforcement learning and teaching","publication_year":1991,"publication_date":"1991-07-14","ids":{"openalex":"https://openalex.org/W50296447","mag":"50296447"},"language":"en","primary_location":{"id":"mag:50296447","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/aaai/aaai91-2.html#Lin91","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National 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":"National Conference on Artificial Intelligence","raw_type":null},"volume":null,"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":[{"author_position":"first","author":{"id":"https://openalex.org/A5107841673","display_name":"Long-Ji Lin","orcid":null,"observed_orcids":[]},"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":true,"raw_author_name":"Long-Ji Lin","raw_affiliation_strings":["School of Computer Science, Carnegie-Mellon University, Pittsburgh, Pennsylvania#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie-Mellon University, Pittsburgh, Pennsylvania#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5107841673"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":13.9164,"has_fulltext":false,"cited_by_count":142,"citation_normalized_percentile":{"value":0.99690761,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"781","last_page":"786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot-programming","display_name":"robot programming","score":0.8230000138282776},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9480000138282776},{"id":"https://openalex.org/keywords/robot-teaching","display_name":"robot teaching","score":0.6290000081062317},{"id":"https://openalex.org/keywords/experiential-learning","display_name":"experiential learning","score":0.6579999923706055},{"id":"https://openalex.org/keywords/learning-speedup","display_name":"learning speedup","score":0.6660000085830688},{"id":"https://openalex.org/keywords/subsumption-architecture","display_name":"subsumption architecture","score":0.9290000200271606},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.7860000133514404},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.7450000047683716}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.8455651998519897},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7527192234992981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297711372375488},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6087266802787781},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.5874404907226562},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5632076263427734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5434409379959106},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5433765649795532},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.502418041229248},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4964490532875061},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.41820281744003296},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.34449148178100586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16866031289100647},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06766870617866516},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06676185131072998},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:50296447","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/aaai/aaai91-2.html#Lin91","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National 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":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6164000034332275}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1500245617","https://openalex.org/W1569296262","https://openalex.org/W1931792391","https://openalex.org/W2097856935","https://openalex.org/W2100677568","https://openalex.org/W6960125083"],"related_works":["https://openalex.org/W7099333908","https://openalex.org/W7165233271","https://openalex.org/W1600022287","https://openalex.org/W2287023718","https://openalex.org/W2903522344","https://openalex.org/W7099234910","https://openalex.org/W1924069939","https://openalex.org/W7213538049","https://openalex.org/W7029977500","https://openalex.org/W1702137226"],"abstract_inverted_index":{"Programming":[0],"robots":[1,13,41,65],"is":[2,8,26],"a":[3,28,36,60,89,107,120],"tedious":[4],"task.":[5],"So,":[6],"there":[7],"growing":[9],"interest":[10],"in":[11,35,106,129,134],"building":[12],"which":[14,20,66,102],"can":[15,44,49,54,67],"learn":[16,97],"by":[17],"themselves.":[18],"Self-improving,":[19],"involves":[21],"trial":[22],"and":[23,31,52,84,95,116],"error,":[24],"however,":[25],"often":[27],"slow":[29],"process":[30],"could":[32,96,114,123],"be":[33,45,50,55],"hazardous":[34],"hostile":[37],"environment.":[38],"By":[39],"teaching":[40],"how":[42],"tasks":[43],"achieved,":[46],"learning":[47,86,91],"time":[48],"shortened":[51],"hazard":[53],"minimized.":[56],"This":[57],"paper":[58],"presents":[59],"general":[61],"approach":[62,83],"to":[63,132],"making":[64],"improve":[68],"their":[69],"performance":[70],"from":[71,76],"experiences":[72],"as":[73,75],"well":[74],"being":[77],"taught.":[78],"Based":[79],"on":[80],"this":[81],"proposed":[82],"other":[85],"speedup":[87],"techniques,":[88],"simulated":[90],"robot":[92,113,122],"was":[93,127],"developed":[94],"three":[98],"moderately":[99],"complex":[100],"behaviors,":[101],"were":[103],"then":[104],"integrated":[105],"subsumption":[108],"style":[109],"so":[110],"that":[111],"the":[112,130,135],"navigate":[115],"recharge":[117],"itself.":[118],"Interestingly,":[119],"real":[121,136],"actually":[124],"use":[125],"what":[126],"learned":[128],"simulator":[131],"operate":[133],"world":[137],"quite":[138],"successfully.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}