{"id":"https://openalex.org/W2922087027","doi":"https://doi.org/10.1109/iros40897.2019.8967849","title":"Policy Distillation and Value Matching in Multiagent Reinforcement Learning","display_name":"Policy Distillation and Value Matching in Multiagent Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2922087027","doi":"https://doi.org/10.1109/iros40897.2019.8967849","mag":"2922087027"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.06592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031054928","display_name":"Samir Wadhwania","orcid":"https://orcid.org/0000-0002-3040-3762"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samir Wadhwania","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033449275","display_name":"Dong Ki Kim","orcid":"https://orcid.org/0000-0002-5195-7852"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong-Ki Kim","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052169592","display_name":"Shayegan Omidshafiei","orcid":"https://orcid.org/0000-0001-7758-1454"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shayegan Omidshafiei","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information and Decision Systems,77 Massachusetts Ave.,MA,USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031054928"],"corresponding_institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02113644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8193","last_page":"8200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9739000201225281,"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":0.9739000201225281,"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":0.8433560132980347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913990378379822},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6076711416244507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5250235199928284},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5235973596572876},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5099684000015259},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4548225998878479},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4518420994281769},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45064598321914673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41898152232170105},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4138602018356323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35990530252456665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14521026611328125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13596713542938232},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1216004490852356}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8433560132980347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913990378379822},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6076711416244507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250235199928284},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5235973596572876},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5099684000015259},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4548225998878479},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4518420994281769},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45064598321914673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41898152232170105},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4138602018356323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35990530252456665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14521026611328125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13596713542938232},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1216004490852356},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iros40897.2019.8967849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.06592","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06592","pdf_url":"https://arxiv.org/pdf/1903.06592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2922087027","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1903.06592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/137155","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.48550/arxiv.1903.06592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.06592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.06592","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06592","pdf_url":"https://arxiv.org/pdf/1903.06592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1497976081","https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2074500080","https://openalex.org/W2107544712","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2294370754","https://openalex.org/W2546571074","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2620645529","https://openalex.org/W2766447205","https://openalex.org/W2963390684","https://openalex.org/W6628598448","https://openalex.org/W6636142636","https://openalex.org/W6640174482","https://openalex.org/W6678250138","https://openalex.org/W6684159546","https://openalex.org/W6684921986","https://openalex.org/W6713411898","https://openalex.org/W6731193076","https://openalex.org/W6732837357","https://openalex.org/W6734517396","https://openalex.org/W6735698609","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6747473740","https://openalex.org/W6760256100"],"related_works":["https://openalex.org/W3003498399","https://openalex.org/W3034236692","https://openalex.org/W11035765","https://openalex.org/W3170834283","https://openalex.org/W3198359393","https://openalex.org/W1902645430","https://openalex.org/W1504806788","https://openalex.org/W2407593946","https://openalex.org/W1584580530","https://openalex.org/W1617621891","https://openalex.org/W3008141518","https://openalex.org/W1497847676","https://openalex.org/W3093342898","https://openalex.org/W2238976967","https://openalex.org/W3014413693","https://openalex.org/W3091819112","https://openalex.org/W2994642062","https://openalex.org/W2735631624","https://openalex.org/W3161195296","https://openalex.org/W2403690381"],"abstract_inverted_index":{"Multiagent":[0],"reinforcement":[1],"learning":[2,37,119],"(MARL)":[3],"algorithms":[4],"have":[5,25],"been":[6],"demonstrated":[7],"on":[8,27],"complex":[9],"tasks":[10],"that":[11,66,111],"require":[12],"the":[13,58,84,90],"coordination":[14],"of":[15,18,60,83,88],"a":[16,67,74,81,97],"team":[17],"multiple":[19],"agents":[20,31,55,106],"to":[21,35,41,56],"complete.":[22],"Existing":[23],"works":[24],"focused":[26],"sharing":[28],"information":[29,50],"between":[30,54],"via":[32],"centralized":[33],"critics":[34],"stabilize":[36],"or":[38],"through":[39,107],"communication":[40],"improve":[42],"performance,":[43],"but":[44],"do":[45],"not":[46],"generally":[47],"consider":[48],"how":[49],"can":[51,70],"be":[52,71],"shared":[53],"address":[57],"curse":[59],"dimensionality":[61],"in":[62,120],"MARL.":[63],"We":[64],"posit":[65],"multiagent":[68,98],"problem":[69,76],"decomposed":[72],"into":[73],"multi-task":[75],"where":[77],"each":[78],"agent":[79],"explores":[80],"subset":[82],"state":[85,92],"space":[86],"instead":[87],"exploring":[89],"entire":[91],"space.":[93],"This":[94],"paper":[95],"introduces":[96],"actor-critic":[99],"algorithm":[100],"for":[101],"combining":[102],"knowledge":[103],"from":[104],"homogeneous":[105],"distillation":[108,114],"and":[109,116,122],"value-matching":[110],"outperforms":[112],"policy":[113],"alone":[115],"allows":[117],"further":[118],"discrete":[121],"continuous":[123],"action":[124],"spaces.":[125]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}