{"id":"https://openalex.org/W4392305726","doi":"https://doi.org/10.5220/0012312700003636","title":"Contextual Online Imitation Learning (COIL): Using Guide Policies in Reinforcement Learning","display_name":"Contextual Online Imitation Learning (COIL): Using Guide Policies in Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392305726","doi":"https://doi.org/10.5220/0012312700003636"},"language":"en","primary_location":{"id":"doi:10.5220/0012312700003636","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012312700003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0012312700003636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102058159","display_name":"Alexander J. Hill","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexander Hill","raw_affiliation_strings":["Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003012942","display_name":"Marc Groefsema","orcid":"https://orcid.org/0000-0002-6044-2519"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marc Groefsema","raw_affiliation_strings":["Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074266137","display_name":"Matthia Sabatelli","orcid":"https://orcid.org/0009-0007-7540-8616"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Matthia Sabatelli","raw_affiliation_strings":["Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061618118","display_name":"Raffaella Carloni","orcid":"https://orcid.org/0000-0002-6051-4332"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Raffaella Carloni","raw_affiliation_strings":["Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068721139","display_name":"Marco Grzegorczyk","orcid":"https://orcid.org/0000-0002-2604-9270"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Grzegorczyk","raw_affiliation_strings":["Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47288861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9955000281333923,"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":0.8708395957946777},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7255668044090271},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7000954747200012},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6890847682952881},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5751084685325623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5674437284469604},{"id":"https://openalex.org/keywords/electromagnetic-coil","display_name":"Electromagnetic coil","score":0.5517065525054932},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.41073712706565857},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39809563755989075},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3980017304420471},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38826167583465576},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21401673555374146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17894384264945984},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07606309652328491}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8708395957946777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7255668044090271},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7000954747200012},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6890847682952881},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5751084685325623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674437284469604},{"id":"https://openalex.org/C30403606","wikidata":"https://www.wikidata.org/wiki/Q2981904","display_name":"Electromagnetic coil","level":2,"score":0.5517065525054932},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.41073712706565857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39809563755989075},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3980017304420471},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38826167583465576},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21401673555374146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17894384264945984},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07606309652328491},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0012312700003636","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012312700003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/a822c17d-4628-46ff-9176-8c81b02a447a","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/a822c17d-4628-46ff-9176-8c81b02a447a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hill, A, Groefsema, M, Sabatelli, M, Carloni, R & Grzegorczyk, M 2024, Contextual Online Imitation Learning (COIL : Using Guide Policies in Reinforcement Learning. in 16th International Conference on Agents and Artificial Intelligence. SciTePress, pp. 178-185, International Conference on Agents and Artificial Intelligence, Rome, Italy, 24/02/2024. https://doi.org/10.5220/0012312700003636","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/a822c17d-4628-46ff-9176-8c81b02a447a","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/a822c17d-4628-46ff-9176-8c81b02a447a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hill, A, Groefsema, M, Sabatelli, M, Carloni, R & Grzegorczyk, M 2024, Contextual Online Imitation Learning (COIL : Using Guide Policies in Reinforcement Learning. in 16th International Conference on Agents and Artificial Intelligence. SciTePress, pp. 178-185, International Conference on Agents and Artificial Intelligence, Rome, Italy, 24/02/2024. https://doi.org/10.5220/0012312700003636","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0012312700003636","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0012312700003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2098787760","https://openalex.org/W2137983211","https://openalex.org/W2165698076","https://openalex.org/W2736601468","https://openalex.org/W2921474818","https://openalex.org/W2953958347","https://openalex.org/W2963277051","https://openalex.org/W2964043796","https://openalex.org/W2976205474","https://openalex.org/W2997874851","https://openalex.org/W3003329097","https://openalex.org/W3090425814","https://openalex.org/W3099905444","https://openalex.org/W3101780148","https://openalex.org/W3199562506","https://openalex.org/W3209866168","https://openalex.org/W4225495521","https://openalex.org/W4286748781","https://openalex.org/W4287181797","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"This":[0,19,93,123],"paper":[1,20,94],"proposes":[2],"a":[3,76,125],"novel":[4],"method":[5],"of":[6,53,60,79,90],"utilising":[7],"guide":[8,55,68,100],"policies":[9,69,101],"in":[10,74,106,128],"Reinforcement":[11,40,114],"Learning":[12,17,32,41,115,133],"problems;":[13],"Contextual":[14],"Online":[15],"Imitation":[16,31,91,132],"(COIL).":[18],"demonstrates":[21,95],"that":[22,63,70,96,102],"COIL":[23,61,142],"can":[24,65,108],"offer":[25],"improved":[26],"performance":[27,105],"over":[28,130],"both":[29],"offline":[30],"methods":[33,89],"such":[34,43],"as":[35,44],"Behavioral":[36],"Cloning,":[37],"and":[38,139],"also":[39,109],"algorithms":[42],"Proximal":[45],"Policy":[46],"Optimisation":[47],"which":[48],"do":[49],"not":[50],"take":[51],"advantage":[52],"existing":[54],"policies.":[56],"An":[57],"important":[58],"characteristic":[59],"is":[62,124],"it":[64,84],"effectively":[66],"utilise":[67],"exhibit":[71],"expert":[72],"behavior":[73],"only":[75],"strict":[77],"subset":[78],"the":[80,137],"state":[81],"space,":[82],"making":[83],"more":[85,120],"flexible":[86],"than":[87],"classical":[88],"Learning.":[92],"through":[97],"using":[98],"COIL,":[99],"achieve":[103],"good":[104],"sub-tasks":[107],"be":[110],"used":[111],"to":[112,118],"help":[113],"agents":[116],"looking":[117],"solve":[119],"complex":[121],"tasks.":[122],"significant":[126],"improvement":[127],"flexibility":[129],"traditional":[131],"methods.":[134],"After":[135],"introducing":[136],"theory":[138],"motivation":[140],"behind":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}