{"id":"https://openalex.org/W2921549305","doi":"https://doi.org/10.5220/0007684908870894","title":"Contextual Action with Multiple Policies Inverse Reinforcement Learning for Behavior Simulation","display_name":"Contextual Action with Multiple Policies Inverse Reinforcement Learning for Behavior Simulation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2921549305","doi":"https://doi.org/10.5220/0007684908870894","mag":"2921549305"},"language":"en","primary_location":{"id":"doi:10.5220/0007684908870894","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007684908870894","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 11th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0007684908870894","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046931302","display_name":"Nahum \u00c1lvarez","orcid":"https://orcid.org/0000-0003-1717-2506"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nahum Alvarez","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology and Japan, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology and Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076716774","display_name":"Itsuki Noda","orcid":"https://orcid.org/0000-0003-1987-5336"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Itsuki Noda","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology and Japan, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology and Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01931267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"887","last_page":"894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7960824966430664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696469783782959},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.630385160446167},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.599342942237854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47053346037864685},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37116849422454834},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1687648892402649},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1319352388381958}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7960824966430664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696469783782959},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.630385160446167},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.599342942237854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47053346037864685},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37116849422454834},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1687648892402649},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1319352388381958},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0007684908870894","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007684908870894","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 11th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0007684908870894","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007684908870894","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 11th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Machine":[0],"learning":[1,53],"is":[2],"a":[3,19,28,49,87],"discipline":[4],"with":[5,18],"many":[6],"simulator-driven":[7],"applications":[8],"oriented":[9],"to":[10,70,86,95,104],"learn":[11],"behavior.":[12],"However,":[13],"behavior":[14,52,78],"simulation":[15],"it":[16],"comes":[17],"number":[20],"of":[21,27,35,38,44,109],"associated":[22],"difficulties,":[23],"like":[24],"the":[25,36,39,42,100,110],"lack":[26],"clear":[29],"reward":[30,73],"function,":[31],"actions":[32],"that":[33,63],"depend":[34],"state":[37],"actor":[40],"and":[41,75,114],"alternation":[43],"different":[45,77],"policies.":[46],"We":[47,82],"present":[48],"method":[50,68,85],"for":[51],"called":[54],"Contextual":[55],"Action":[56],"Multiple":[57],"Policy":[58],"Inverse":[59],"Reinforcement":[60],"Learning":[61],"(CAMP-IRL)":[62],"tackles":[64],"those":[65],"factors.":[66],"Our":[67],"allows":[69],"extract":[71],"multiple":[72],"functions":[74],"generates":[76],"profiles":[79],"from":[80],"them.":[81],"applied":[83],"our":[84],"large":[88],"scale":[89],"crowd":[90],"simulator":[91],"using":[92],"intelligent":[93],"agents":[94],"imitate":[96],"pedestrian":[97],"behavior,":[98],"making":[99],"virtual":[101],"pedestrians":[102],"able":[103],"switch":[105],"between":[106],"behaviors":[107],"depending":[108],"goal":[111],"they":[112],"have":[113],"navigating":[115],"efficiently":[116],"across":[117],"unknown":[118],"environments.":[119]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}