{"id":"https://openalex.org/W4296474733","doi":"https://doi.org/10.1109/cog51982.2022.9893655","title":"Regularized Soft Actor-Critic for Behavior Transfer Learning","display_name":"Regularized Soft Actor-Critic for Behavior Transfer Learning","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296474733","doi":"https://doi.org/10.1109/cog51982.2022.9893655"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","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/A5029152749","display_name":"Mingxi Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mingxi Tan","raw_affiliation_strings":["Ubisoft La Forge Ubisoft,Chengdu,China","Ubisoft La Forge Ubisoft, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge Ubisoft,Chengdu,China","institution_ids":[]},{"raw_affiliation_string":"Ubisoft La Forge Ubisoft, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015880774","display_name":"Andong Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andong Tian","raw_affiliation_strings":["Ubisoft La Forge Ubisoft,Chengdu,China","Ubisoft La Forge Ubisoft, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge Ubisoft,Chengdu,China","institution_ids":[]},{"raw_affiliation_string":"Ubisoft La Forge Ubisoft, Chengdu, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027101473","display_name":"Ludovic Denoyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ludovic Denoyer","raw_affiliation_strings":["Ubisoft La Forge Ubisoft,Chengdu,China","Ubisoft La Forge Ubisoft, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge Ubisoft,Chengdu,China","institution_ids":[]},{"raw_affiliation_string":"Ubisoft La Forge Ubisoft, Chengdu, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029152749"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2652,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61375863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"516","last_page":"519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.993399977684021,"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":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7463299036026001},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6986662149429321},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6320801377296448},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6177743673324585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5705175995826721},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44186657667160034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3960355520248413},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3410012722015381},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32880300283432007},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11497199535369873},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09983780980110168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.088163822889328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7463299036026001},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6986662149429321},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6320801377296448},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6177743673324585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705175995826721},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44186657667160034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3960355520248413},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3410012722015381},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32880300283432007},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11497199535369873},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09983780980110168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.088163822889328},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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:10.1109/cog51982.2022.9893655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1931877416","https://openalex.org/W2051228319","https://openalex.org/W2530195778","https://openalex.org/W2949561945","https://openalex.org/W2950596486","https://openalex.org/W2963277051","https://openalex.org/W2963508354","https://openalex.org/W2969489701","https://openalex.org/W2994712737","https://openalex.org/W3037804676","https://openalex.org/W3094224934","https://openalex.org/W4288347236","https://openalex.org/W6630965284","https://openalex.org/W6640174482","https://openalex.org/W6718092244","https://openalex.org/W6728073343","https://openalex.org/W6734517396","https://openalex.org/W6745347688","https://openalex.org/W6754554871","https://openalex.org/W6766952794","https://openalex.org/W6768425981","https://openalex.org/W6771280675","https://openalex.org/W6780312303","https://openalex.org/W6785187516"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Existing":[0],"imitation":[1,79,106],"learning":[2],"methods":[3,39],"mainly":[4],"focus":[5],"on":[6,117],"making":[7],"an":[8,42],"agent":[9,43],"effectively":[10],"mimic":[11],"a":[12,30,34,47,59,66,111],"demonstrated":[13,48],"behavior,":[14],"but":[15],"do":[16],"not":[17],"address":[18],"the":[19,23,27,55,74,78,82,95,105],"potential":[20],"contradiction":[21],"between":[22],"behavior":[24,49],"style":[25],"and":[26,77,104],"objective":[28,57,98],"of":[29,37,58],"task.":[31,60],"There":[32],"is":[33,92,108],"general":[35],"lack":[36],"efficient":[38],"that":[40],"allow":[41],"to":[44,50,122],"partially":[45],"imitate":[46],"varying":[51],"degrees,":[52],"while":[53],"completing":[54],"main":[56,75,90],"In":[61],"this":[62],"paper":[63],"we":[64],"propose":[65],"method":[67,116],"called":[68],"Regularized":[69],"Soft":[70,101],"Actor-Critic":[71,102],"which":[72],"formulates":[73],"task":[76,80,91,107],"under":[81],"Constrained":[83],"Markov":[84],"Decision":[85],"Process":[86],"framework":[87],"(CMDP).":[88],"The":[89],"defined":[93,109],"as":[94,110],"maximum":[96],"entropy":[97],"used":[99],"in":[100],"(SAC)":[103],"constraint.":[112],"We":[113],"evaluate":[114],"our":[115],"continuous":[118],"control":[119],"tasks":[120],"relevant":[121],"video":[123],"games":[124],"applications.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}