{"id":"https://openalex.org/W4390547995","doi":"https://doi.org/10.1145/3632410.3632430","title":"DSDF: Coordinated look-ahead strategy in multi-agent reinforcement learning with noisy agents","display_name":"DSDF: Coordinated look-ahead strategy in multi-agent reinforcement learning with noisy agents","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390547995","doi":"https://doi.org/10.1145/3632410.3632430"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5019643071","display_name":"Satheesh K. Perepu","orcid":"https://orcid.org/0000-0002-5132-2144"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satheesh Kumar Perepu","raw_affiliation_strings":["Ericsson Research, India"],"raw_orcid":"https://orcid.org/0000-0002-5132-2144","affiliations":[{"raw_affiliation_string":"Ericsson Research, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089847093","display_name":"Kripa Nath Dey","orcid":"https://orcid.org/0009-0002-5795-9063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaushik Dey","raw_affiliation_strings":["Ericsson Research, India"],"raw_orcid":"https://orcid.org/0009-0002-5795-9063","affiliations":[{"raw_affiliation_string":"Ericsson Research, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101751934","display_name":"Abir Das","orcid":"https://orcid.org/0000-0002-2327-1618"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abir Das","raw_affiliation_strings":["Indian Institue of Technology Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0002-2327-1618","affiliations":[{"raw_affiliation_string":"Indian Institue of Technology Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019643071"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00212234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8257439732551575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700180411338806},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.642200231552124},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.628191351890564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5318205952644348},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5278744101524353},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5120809674263},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4577552080154419},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4418465793132782},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4159961938858032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38878685235977173}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8257439732551575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700180411338806},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.642200231552124},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.628191351890564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318205952644348},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5278744101524353},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5120809674263},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4577552080154419},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4418465793132782},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4159961938858032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38878685235977173},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.6399999856948853,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2915117209","https://openalex.org/W2962764167","https://openalex.org/W2962990769","https://openalex.org/W2969195240","https://openalex.org/W2997502221","https://openalex.org/W3021603984","https://openalex.org/W3131448887","https://openalex.org/W3134141999","https://openalex.org/W3163926178","https://openalex.org/W3205321526","https://openalex.org/W4288049695","https://openalex.org/W4306786778","https://openalex.org/W4362519817"],"related_works":["https://openalex.org/W2006651773","https://openalex.org/W2494202692","https://openalex.org/W2161520603","https://openalex.org/W2612836981","https://openalex.org/W2604958989","https://openalex.org/W2618716983","https://openalex.org/W2620638075","https://openalex.org/W1586030051","https://openalex.org/W2372480026","https://openalex.org/W2066202387"],"abstract_inverted_index":{"Existing":[0],"methods":[1,57],"of":[2,21,37,77,82,118,131,147,164,171,205],"Multi-Agent":[3],"Reinforcement":[4],"learning,":[5],"involving":[6],"Centralized":[7],"Training":[8],"and":[9,41,91,116],"Decentralized":[10],"execution,":[11],"attempt":[12],"to":[13,24,52,86,94,112,127,178],"train":[14],"the":[15,32,38,46,55,78,87,102,109,114,119,123,145,149,152,161,165,169,203,206],"agents":[16,39,103,121,125,175],"towards":[17],"learning":[18],"a":[19,75,100,185],"pattern":[20],"coordinated":[22],"actions":[23,44,48],"arrive":[25],"at":[26],"optimal":[27],"joint":[28],"policy.":[29],"However,":[30],"during":[31],"execution":[33],"phase,":[34],"if":[35],"some":[36,174],"degrade":[40],"perform":[42],"noisy":[43,120,124],"(not":[45],"same":[47],"suggested":[49],"by":[50],"policy)":[51],"varying":[53],"degrees,":[54],"above":[56],"provide":[58],"poor":[59],"coordination.":[60],"In":[61,98,134],"this":[62],"paper,":[63],"we":[64],"show":[65,202],"how":[66],"such":[67,99,189],"random":[68],"noise":[69],"in":[70,89,106,129,173],"agents,":[71],"which":[72,104,188],"could":[73],"be":[74,192],"result":[76],"degradation":[79,148,172],"or":[80],"aging":[81],"robots,":[83],"can":[84,191],"add":[85],"uncertainty":[88],"coordination":[90],"thereby":[92,159],"contribute":[93],"unsatisfactory":[95],"global":[96,162],"rewards.":[97],"scenario,":[101],"are":[105],"accordance":[107],"with":[108,211],"policy":[110],"have":[111,126],"understand":[113],"behavior":[115],"limitations":[117],"while":[122],"plan":[128],"cognizance":[130],"their":[132],"limitations.":[133],"our":[135,182],"proposed":[136],"method,":[137],"Deep":[138],"Stochastic":[139],"Discount":[140],"Factor":[141],"(DSDF),":[142],"based":[143],"on":[144,199],"degree":[146,170],"algorithm":[150],"tunes":[151],"discount":[153],"factor":[154],"for":[155],"each":[156],"agent":[157],"uniquely,":[158],"altering":[160],"planning":[163],"agents.":[166],"Moreover,":[167],"given":[168],"is":[176],"expected":[177],"change":[179],"over":[180],"time,":[181],"method":[183],"provides":[184],"framework":[186],"under":[187],"changes":[190],"incrementally":[193],"addressed":[194],"without":[195],"extensive":[196],"retraining.":[197],"Results":[198],"benchmark":[200],"environments":[201],"efficacy":[204],"DSDF":[207],"approach":[208],"when":[209],"compared":[210],"existing":[212],"approaches.":[213]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}