{"id":"https://openalex.org/W7124207244","doi":"https://doi.org/10.65109/umoy2342","title":"Directing Policy Search with Interactively Taught Via-Points","display_name":"Directing Policy Search with Interactively Taught Via-Points","publication_year":2016,"publication_date":"2016-05-09","ids":{"openalex":"https://openalex.org/W7124207244","doi":"https://doi.org/10.65109/umoy2342"},"language":"en","primary_location":{"id":"doi:10.65109/umoy2342","doi":"https://doi.org/10.65109/umoy2342","is_oa":false,"landing_page_url":"https://doi.org/10.65109/umoy2342","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"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/A5084125996","display_name":"Yannick Schroecker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannick Schroecker","raw_affiliation_strings":["Georgia Institute of technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024068845","display_name":"Heni Ben Amor","orcid":"https://orcid.org/0000-0002-9896-8217","observed_orcids":["https://orcid.org/0000-0002-9896-8217"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heni Ben Amor","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066797327","display_name":"Andrea L. Thomaz","orcid":"https://orcid.org/0000-0002-3734-964X","observed_orcids":["https://orcid.org/0000-0002-3734-964X"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Thomaz","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39664894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1052","last_page":"1059"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0010999999940395355,"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/T10982","display_name":"Motor Control and Adaptation","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-search","display_name":"policy search","score":0.9909999966621399},{"id":"https://openalex.org/keywords/interactive-teaching-methods","display_name":"interactive teaching methods","score":0.5929999947547913},{"id":"https://openalex.org/keywords/trajectory-space","display_name":"trajectory space","score":0.4169999957084656},{"id":"https://openalex.org/keywords/policy-initialization","display_name":"policy initialization","score":0.640999972820282},{"id":"https://openalex.org/keywords/demonstration-based-learning","display_name":"demonstration-based learning","score":0.6949999928474426},{"id":"https://openalex.org/keywords/robot-manipulators","display_name":"robot manipulators","score":0.7239999771118164},{"id":"https://openalex.org/keywords/object-insertion","display_name":"object insertion","score":0.6850000023841858}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7610999941825867},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6952999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.635699987411499},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360999703407288},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27309998869895935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.65109/umoy2342","doi":"https://doi.org/10.65109/umoy2342","is_oa":false,"landing_page_url":"https://doi.org/10.65109/umoy2342","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"}],"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/W2973127235","https://openalex.org/W4389650811","https://openalex.org/W2181324803","https://openalex.org/W625801830","https://openalex.org/W7095825025","https://openalex.org/W2121103318","https://openalex.org/W4416155345","https://openalex.org/W3016030121","https://openalex.org/W1685912164","https://openalex.org/W2012392077"],"abstract_inverted_index":{"Policy":[0],"search":[1,50,95],"has":[2,28],"been":[3,29],"successfully":[4],"applied":[5],"to":[6,31,36,97,103,120,138],"robot":[7,130],"motor":[8],"learning":[9,87],"problems.":[10],"However,":[11],"for":[12,48,77,82],"moderately":[13],"complex":[14],"tasks":[15],"the":[16,52,86,94,104,108,115],"necessity":[17],"of":[18,54,64,117],"good":[19,123],"heuristics":[20],"or":[21],"initialization":[22,78],"still":[23],"arises.":[24],"One":[25],"method":[26,134,153],"that":[27,99,132],"used":[30,76],"alleviate":[32],"this":[33,57,90],"problem":[34],"is":[35],"utilize":[37],"demonstrations":[38,66],"obtained":[39],"by":[40],"a":[41,45,122,128,143,147,156],"human":[42],"teacher":[43],"as":[44,67,79,81],"starting":[46],"point":[47],"policy":[49],"in":[51,142],"space":[53,96],"trajectories.":[55],"In":[56],"paper":[58],"we":[59,92],"describe":[60],"an":[61,140],"alternative":[62],"way":[63],"giving":[65],"soft":[68],"via-points":[69,106],"and":[70,111,150],"show":[71,126],"how":[72],"they":[73],"can":[74,135],"be":[75,101],"well":[80],"active":[83],"corrections":[84],"during":[85],"process.":[88],"With":[89],"approach,":[91],"restrict":[93],"trajectories":[98],"will":[100],"close":[102],"taught":[105,109],"at":[107],"time":[110],"thereby":[112],"significantly":[113],"reduce":[114],"number":[116],"samples":[118],"necessary":[119],"learn":[121,137],"policy.":[124],"We":[125],"with":[127,145],"simulated":[129],"arm":[131],"our":[133,152],"efficiently":[136],"insert":[139],"object":[141],"hole":[144],"just":[146],"minimal":[148],"demonstration":[149],"evaluate":[151],"further":[154],"on":[155],"synthetic":[157],"letter":[158],"reproduction":[159],"task.":[160]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-15T00:00:00"}
