{"id":"https://openalex.org/W3176014111","doi":"https://doi.org/10.5555/3463952.3464191","title":"Approximate Difference Rewards for Scalable Multigent Reinforcement Learning.","display_name":"Approximate Difference Rewards for Scalable Multigent Reinforcement Learning.","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3176014111","doi":"https://doi.org/10.5555/3463952.3464191","mag":"3176014111"},"language":"en","primary_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7025","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7025&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.5555/3463952.3464191","raw_type":"Conference Proceeding Article"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/6901","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012983833","display_name":"Arambam James Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arambam James Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Akshat Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akshat Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015466370","display_name":"Hoong Chuin Lau","orcid":"https://orcid.org/0000-0002-5326-411X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoong Chuin Lau","raw_affiliation_strings":[],"raw_orcid":null,"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1655","last_page":"1657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9908999800682068,"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":0.9872000217437744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8053752183914185},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6324912309646606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5880904793739319},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5815455913543701},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47763457894325256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35949522256851196},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23244556784629822},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09478828310966492},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0659031867980957}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8053752183914185},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6324912309646606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5880904793739319},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5815455913543701},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47763457894325256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35949522256851196},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23244556784629822},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09478828310966492},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0659031867980957}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7025","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7025&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.5555/3463952.3464191","raw_type":"Conference Proceeding Article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7904","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6901","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (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":null,"raw_type":"Conference Proceeding Article"},{"id":"mag:3176014111","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/atal/aamas2021.html#SinghKL21","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7904","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6901","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (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":null,"raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W1969302761","https://openalex.org/W2098877483","https://openalex.org/W2122763142","https://openalex.org/W2131648741","https://openalex.org/W2161061197","https://openalex.org/W2410877381","https://openalex.org/W2608544166","https://openalex.org/W2891663723","https://openalex.org/W2943541269","https://openalex.org/W2962966033","https://openalex.org/W2963039558","https://openalex.org/W2963407617","https://openalex.org/W2991626785","https://openalex.org/W3037469505","https://openalex.org/W3037725723"],"related_works":["https://openalex.org/W2992584149","https://openalex.org/W2368059979","https://openalex.org/W2929555137","https://openalex.org/W3213112773","https://openalex.org/W2330011152","https://openalex.org/W3195079419","https://openalex.org/W1018202636","https://openalex.org/W3161889611","https://openalex.org/W2914477451","https://openalex.org/W2884037041","https://openalex.org/W3034278799","https://openalex.org/W1513468570","https://openalex.org/W2270510788","https://openalex.org/W94964689","https://openalex.org/W2978070926","https://openalex.org/W2268920910","https://openalex.org/W2367922714","https://openalex.org/W2617492244","https://openalex.org/W2051854243","https://openalex.org/W1497976081"],"abstract_inverted_index":{"Agency":[0],"for":[1],"Science,":[2],"Technology":[3],"and":[4],"Research":[5,8],"(A*STAR);":[6],"National":[7],"Foundation":[9],"(NRF)":[10],"Singapore":[11]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
