{"id":"https://openalex.org/W3008894209","doi":"https://doi.org/10.1109/ssci44817.2019.9002777","title":"Multi-agent Reinforcement Learning in Spatial Domain Tasks using Inter Subtask Empowerment Rewards","display_name":"Multi-agent Reinforcement Learning in Spatial Domain Tasks using Inter Subtask Empowerment Rewards","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008894209","doi":"https://doi.org/10.1109/ssci44817.2019.9002777","mag":"3008894209"},"language":"en","primary_location":{"id":"doi:10.1109/ssci44817.2019.9002777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/6199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081835375","display_name":"Shubham Pateria","orcid":"https://orcid.org/0000-0002-6507-4479"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shubham Pateria","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062773086","display_name":"Budhitama Subagdja","orcid":"https://orcid.org/0000-0001-9774-0264"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Budhitama Subagdja","raw_affiliation_strings":["ST Engineering-NTU Corporate Laboratory, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"ST Engineering-NTU Corporate Laboratory, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ah-Hwee Tan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081835375"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.289,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69059025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8681919574737549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.742842435836792},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5754414796829224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5298967957496643},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.436176598072052},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42733675241470337},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.343768447637558},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13337528705596924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06960278749465942},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05623900890350342}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8681919574737549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742842435836792},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5754414796829224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298967957496643},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.436176598072052},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42733675241470337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.343768447637558},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13337528705596924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06960278749465942},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05623900890350342},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssci44817.2019.9002777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7202","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6199","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/SSCI44817.2019.9002777","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7202","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6199","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/SSCI44817.2019.9002777","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W189510620","https://openalex.org/W1592847719","https://openalex.org/W1982678075","https://openalex.org/W2036762299","https://openalex.org/W2074304756","https://openalex.org/W2096145798","https://openalex.org/W2109910161","https://openalex.org/W2110906765","https://openalex.org/W2118318536","https://openalex.org/W2121517924","https://openalex.org/W2154902490","https://openalex.org/W2160371091","https://openalex.org/W2520157010","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2793234362","https://openalex.org/W2949267040","https://openalex.org/W2962686687","https://openalex.org/W2964227312","https://openalex.org/W2989068617","https://openalex.org/W3117280628","https://openalex.org/W4214717370","https://openalex.org/W4299802797","https://openalex.org/W6607700667","https://openalex.org/W6676769901","https://openalex.org/W6677834374","https://openalex.org/W6683821272","https://openalex.org/W6727007750","https://openalex.org/W6727349600","https://openalex.org/W6734215269","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6749859352","https://openalex.org/W6758714175"],"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/W2086122291","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"In":[0,118],"the":[1,25,32,35,51,56,61,70,87,112,149,161,169,186,206,215,218,224,232],"complex":[2,74],"multi-agent":[3],"tasks,":[4],"various":[5,67,116,211],"agents":[6,81,93,212],"must":[7],"cooperate":[8],"to":[9,16,49,55,65,110,144,160,167],"distribute":[10],"relevant":[11,26],"subtasks":[12,52],"among":[13,217],"each":[14],"other":[15,92,152],"achieve":[17],"joint":[18,62,71],"task":[19,36,63,72,89,101,163],"objectives.":[20],"An":[21],"agent's":[22],"choice":[23],"of":[24,80,85,126,151,210],"subtask":[27,181,207,225],"changes":[28,33],"over":[29],"time":[30],"with":[31],"in":[34,53,107,135,158,165,194,214],"environment":[37,57],"state.":[38],"Multi-agent":[39,132],"Hierarchical":[40],"Reinforcement":[41],"Learning":[42],"(MAHRL)":[43],"provides":[44],"an":[45,137,145],"approach":[46,125],"for":[47,115],"learning":[48],"select":[50],"response":[54],"states,":[58],"by":[59,189],"using":[60],"rewards":[64],"train":[66],"agents.":[68,117],"When":[69],"involves":[73],"inter-agent":[75,170],"dependencies,":[76],"only":[77],"a":[78,123,195],"subset":[79],"might":[82,103],"be":[83,105],"capable":[84],"reaching":[86],"rewarding":[88],"states":[90],"while":[91],"take":[94],"precursory":[95],"or":[96],"intermediate":[97],"roles.":[98],"The":[99],"delayed":[100],"reward":[102,164],"not":[104],"sufficient":[106],"such":[108],"tasks":[109],"learn":[111,179,205,223],"coordinating":[113],"policies":[114,209],"this":[119],"paper,":[120],"we":[121],"introduce":[122],"novel":[124],"MAHRL":[127,234],"called":[128],"Inter-Subtask":[129,138],"Empowerment":[130,139],"based":[131],"Options":[133],"(ISEMO)":[134],"which":[136,147],"Reward":[140],"(ISER)":[141],"is":[142,156],"given":[143,157],"agent":[146],"enables":[148],"precondition(s)":[150],"agents'":[153],"subtasks.":[154],"ISER":[155],"addition":[159],"domain":[162,200],"order":[166],"improve":[168],"coordination.":[171],"ISEMO":[172,203],"also":[173],"incorporates":[174],"options":[175],"model":[176],"that":[177,202],"can":[178,204],"parameterized":[180],"termination":[182,191,226],"functions":[183],"and":[184,198,228],"relax":[185],"limitations":[187],"posed":[188],"hand-crafted":[190],"conditions.":[192],"Experiments":[193],"spatial":[196],"Search":[197],"Rescue":[199],"show":[201],"selection":[208],"grounded":[213],"inter-dependencies":[216],"agents,":[219],"as":[220,222],"well":[221],"conditions,":[227],"perform":[229],"better":[230],"than":[231],"standard":[233],"technique.":[235]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}