{"id":"https://openalex.org/W4385410008","doi":"https://doi.org/10.1162/neco_a_01607","title":"Learning Intention-Aware Policies in Deep Reinforcement Learning","display_name":"Learning Intention-Aware Policies in Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385410008","doi":"https://doi.org/10.1162/neco_a_01607","pmid":"https://pubmed.ncbi.nlm.nih.gov/37523456"},"language":"en","primary_location":{"id":"doi:10.1162/neco_a_01607","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01607","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5049071926","display_name":"Tingting Zhao","orcid":"https://orcid.org/0000-0001-9376-6715"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tingting Zhao","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066900102","display_name":"Shuai Wu","orcid":"https://orcid.org/0000-0001-7713-1808"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuai Wu","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003733165","display_name":"Guixi Li","orcid":"https://orcid.org/0000-0002-7246-5312"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guixi Li","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064335604","display_name":"Yarui Chen","orcid":"https://orcid.org/0000-0002-1467-1716"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yarui Chen","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, P.R.C. tingting@tust.edu.cn","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445445","display_name":"Gang Niu","orcid":"https://orcid.org/0000-0002-8813-8885"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gang Niu","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan gang.niu.ml@gmail.com"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan gang.niu.ml@gmail.com","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["Graduate School of Frontier Sciences, University of Tokyo, Tokyo 277-8561, Japan sugi@k.u-tokyo.ac.jp","RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo, Tokyo 277-8561, Japan sugi@k.u-tokyo.ac.jp","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003733165","https://openalex.org/A5049071926","https://openalex.org/A5064335604","https://openalex.org/A5066900102","https://openalex.org/A5072744508","https://openalex.org/A5101445445"],"corresponding_institution_ids":["https://openalex.org/I132369690","https://openalex.org/I4210126580","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5432473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":"10","first_page":"1657","last_page":"1677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.982200026512146,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9772999882698059,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9027014374732971},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6766916513442993},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6450899839401245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6435078382492065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5551517009735107},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5373572111129761},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.530346691608429},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.510200023651123},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4686811566352844},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4374193549156189},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3748682737350464},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11076578497886658},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08809146285057068}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9027014374732971},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6766916513442993},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6450899839401245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6435078382492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5551517009735107},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5373572111129761},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.530346691608429},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4686811566352844},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4374193549156189},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3748682737350464},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11076578497886658},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08809146285057068},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/neco_a_01607","is_oa":false,"landing_page_url":"https://doi.org/10.1162/neco_a_01607","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:37523456","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37523456","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1522301498","https://openalex.org/W2010581677","https://openalex.org/W2032558547","https://openalex.org/W2041367235","https://openalex.org/W2101524054","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2122925692","https://openalex.org/W2145339207","https://openalex.org/W2149350210","https://openalex.org/W2155007355","https://openalex.org/W2160269795","https://openalex.org/W2201581102","https://openalex.org/W2492794003","https://openalex.org/W2559655401","https://openalex.org/W2604272474","https://openalex.org/W2736601468","https://openalex.org/W2963864421","https://openalex.org/W2980225636","https://openalex.org/W3005053211","https://openalex.org/W3007852061","https://openalex.org/W3033820094","https://openalex.org/W3041202696","https://openalex.org/W3081661003","https://openalex.org/W3099098707","https://openalex.org/W4287997992","https://openalex.org/W4288348115","https://openalex.org/W4293391222","https://openalex.org/W4293517721","https://openalex.org/W4298857966","https://openalex.org/W4365799809","https://openalex.org/W6607097208","https://openalex.org/W6674884181","https://openalex.org/W6682849425","https://openalex.org/W6683153233","https://openalex.org/W6683195989","https://openalex.org/W6683436435","https://openalex.org/W6692846177","https://openalex.org/W6718140377","https://openalex.org/W6772515299","https://openalex.org/W6796339008"],"related_works":["https://openalex.org/W2912415823","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W3096874164","https://openalex.org/W2136202932","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2089415692","https://openalex.org/W4294873804","https://openalex.org/W3148138296"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,86],"(DRL)":[3],"provides":[4],"an":[5,8,83,98,132],"agent":[6,74],"with":[7,118],"optimal":[9],"policy":[10,19,31,58,85,100,108,151],"so":[11],"as":[12,46],"to":[13,41,62,69,75],"maximize":[14],"the":[15,26,52,56,64,73,103,107,115,119,124,127,135,146,149,153,159],"cumulative":[16,116],"rewards.":[17],"The":[18],"defined":[20],"in":[21,55,88,152],"DRL":[22],"mainly":[23],"depends":[24],"on":[25],"state,":[27],"historical":[28],"memory,":[29],"and":[30,71,126,158],"model":[32],"parameters.":[33],"However,":[34],"we":[35,81,95,130,144],"humans":[36,70],"usually":[37],"take":[38],"actions":[39,77],"according":[40],"our":[42],"own":[43],"intentions,":[44,80],"such":[45],"moving":[47],"fast":[48],"or":[49],"slow,":[50],"besides":[51],"elements":[53],"included":[54],"traditional":[57],"models.":[59],"In":[60],"order":[61],"make":[63,72],"action-choosing":[65],"mechanism":[66],"more":[67],"similar":[68],"select":[76],"that":[78,138],"incorporate":[79],"propose":[82],"intention-aware":[84,99,150],"method":[87],"this":[89,93],"letter":[90],"To":[91],"formalize":[92],"process,":[94],"first":[96],"define":[97],"by":[101,113],"incorporating":[102],"intention":[104,125],"information":[105,121],"into":[106],"model,":[109],"which":[110],"is":[111],"learned":[112],"maximizing":[114],"rewards":[117],"mutual":[120],"(MI)":[122],"between":[123],"action.":[128],"Then":[129],"derive":[131],"approximation":[133],"of":[134,148],"MI":[136],"objective":[137],"can":[139],"be":[140],"optimized":[141],"efficiently.":[142],"Finally,":[143],"demonstrate":[145],"effectiveness":[147],"classical":[154],"MuJoCo":[155],"control":[156],"task":[157],"multigoal":[160],"continuous":[161],"chain":[162],"walking":[163],"task.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-08T23:21:52.890332","created_date":"2025-10-10T00:00:00"}