{"id":"https://openalex.org/W3036178917","doi":null,"title":"Open Ad Hoc Teamwork using Graph-based Policy Learning","display_name":"Open Ad Hoc Teamwork using Graph-based Policy Learning","publication_year":2020,"publication_date":"2020-06-18","ids":{"openalex":"https://openalex.org/W3036178917","mag":"3036178917"},"language":"en","primary_location":{"id":"mag:3036178917","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.10412","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2006.10412","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074220260","display_name":"Arrasy Rahman","orcid":"https://orcid.org/0000-0003-1006-9653","observed_orcids":["https://orcid.org/0000-0003-1006-9653"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arrasy Rahman","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1006-9653","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091088085","display_name":"Niklas H\u00f6pner","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niklas H\u00f6pner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047256432","display_name":"Filippos Christianos","orcid":"https://orcid.org/0000-0002-4230-2846","observed_orcids":["https://orcid.org/0000-0002-4230-2846"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Filippos Christianos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4230-2846","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073739308","display_name":"Stefano V. Albrecht","orcid":"https://orcid.org/0000-0002-8735-1465","observed_orcids":["https://orcid.org/0000-0002-8735-1465"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefano V. Albrecht","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8735-1465","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9839000105857849,"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":0.9839000105857849,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.005200000014156103,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0008999999845400453,"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/ad-hoc-teamwork","display_name":"ad hoc teamwork","score":0.8709999918937683},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7620000243186951},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.7179999947547913},{"id":"https://openalex.org/keywords/value-decomposition","display_name":"value decomposition","score":0.75},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.8650000095367432}],"concepts":[{"id":"https://openalex.org/C111226992","wikidata":"https://www.wikidata.org/wiki/Q626225","display_name":"Teamwork","level":2,"score":0.8234959244728088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285729646682739},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6511898040771484},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6247819662094116},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5322138071060181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48153001070022583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41881483793258667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34713590145111084},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2407028079032898},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3036178917","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.10412","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3036178917","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.10412","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W160961942","https://openalex.org/W938188971","https://openalex.org/W1606056663","https://openalex.org/W2064675550","https://openalex.org/W2116341502","https://openalex.org/W2118318536","https://openalex.org/W2136418668","https://openalex.org/W2139993574","https://openalex.org/W2145339207","https://openalex.org/W2149347032","https://openalex.org/W2172933221","https://openalex.org/W2260756217","https://openalex.org/W2758442112","https://openalex.org/W2788212683","https://openalex.org/W2788266634","https://openalex.org/W2805516822","https://openalex.org/W2807741983","https://openalex.org/W2892753736","https://openalex.org/W2946439115","https://openalex.org/W2951218345","https://openalex.org/W2962941327","https://openalex.org/W2963502082","https://openalex.org/W2966826386","https://openalex.org/W2987046690","https://openalex.org/W2996786181","https://openalex.org/W3093287223"],"related_works":["https://openalex.org/W3144282267","https://openalex.org/W4305031576","https://openalex.org/W6958873808","https://openalex.org/W7117389415","https://openalex.org/W4392182249","https://openalex.org/W4394906622","https://openalex.org/W4417095844","https://openalex.org/W2739571258","https://openalex.org/W2996786181","https://openalex.org/W4386791028"],"abstract_inverted_index":{"Ad":[0],"hoc":[1],"teamwork":[2],"is":[3,38,115],"the":[4,34,57],"challenging":[5],"problem":[6],"of":[7,36,50],"designing":[8],"an":[9],"autonomous":[10],"agent":[11,73,91,104],"which":[12,33,82,106],"can":[13,83,107],"adapt":[14,109],"quickly":[15],"to":[16,53,70,110,117,120],"collaborate":[17],"with":[18,87],"previously":[19],"unknown":[20],"teammates.":[21],"Prior":[22],"work":[23],"in":[24,32,103],"this":[25,41],"area":[26],"has":[27],"focused":[28],"on":[29,66],"closed":[30],"teams":[31,46,122],"number":[35],"agents":[37,49],"fixed.":[39],"In":[40],"work,":[42],"we":[43],"consider":[44],"open":[45],"by":[47],"allowing":[48],"varying":[51,79],"types":[52],"enter":[54],"and":[55,75,114],"leave":[56],"team":[58,80,112],"without":[59],"prior":[60],"notification.":[61],"Our":[62],"proposed":[63],"solution":[64],"builds":[65],"graph":[67],"neural":[68],"networks":[69],"learn":[71],"scalable":[72],"models":[74],"value":[76],"decompositions":[77],"under":[78],"sizes,":[81],"be":[84],"jointly":[85],"trained":[86],"a":[88],"reinforcement":[89],"learning":[90],"using":[92],"discounted":[93],"returns":[94],"objectives.":[95],"We":[96],"demonstrate":[97],"empirically":[98],"that":[99],"our":[100],"approach":[101],"results":[102],"policies":[105],"robustly":[108],"dynamic":[111],"composition,":[113],"able":[116],"effectively":[118],"generalize":[119],"larger":[121],"than":[123],"were":[124],"seen":[125],"during":[126],"training.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-06-25T00:00:00"}