{"id":"https://openalex.org/W4411945997","doi":"https://doi.org/10.1145/3736252.3742538","title":"Relative Monte Carlo for Reinforcement Learning","display_name":"Relative Monte Carlo for Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4411945997","doi":"https://doi.org/10.1145/3736252.3742538"},"language":"en","primary_location":{"id":"doi:10.1145/3736252.3742538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736252.3742538","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736252.3742538","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM Conference on Economics and Computation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3736252.3742538","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041371017","display_name":"Audrey Bazerghi","orcid":"https://orcid.org/0000-0001-6346-8952"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Audrey Bazerghi","raw_affiliation_strings":["Kellogg School of Management, Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-6346-8952","affiliations":[{"raw_affiliation_string":"Kellogg School of Management, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866053","display_name":"S\u00e9bastien Martin","orcid":"https://orcid.org/0000-0003-1021-6086"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Martin","raw_affiliation_strings":["Kellogg School of Management, Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-1021-6086","affiliations":[{"raw_affiliation_string":"Kellogg School of Management, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005574703","display_name":"Garrett van Ryzin","orcid":"https://orcid.org/0000-0002-7901-6771"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garrett van Ryzin","raw_affiliation_strings":["Amazon, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-7901-6771","affiliations":[{"raw_affiliation_string":"Amazon, New York, NY, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041371017"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07396508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"342","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.576200008392334,"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/T10320","display_name":"Neural Networks and Applications","score":0.576200008392334,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.5619999766349792,"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/monte-carlo-method","display_name":"Monte Carlo method","score":0.7667108178138733},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7304656505584717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6710801720619202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43100103735923767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14725756645202637},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11945775151252747}],"concepts":[{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.7667108178138733},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7304656505584717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6710801720619202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43100103735923767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14725756645202637},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11945775151252747}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736252.3742538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736252.3742538","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736252.3742538","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM Conference on Economics and Computation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3736252.3742538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736252.3742538","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736252.3742538","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM Conference on Economics and Computation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411945997.pdf","grobid_xml":"https://content.openalex.org/works/W4411945997.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"We":[0],"propose":[1],"and":[2,30,50,64,88,145,168],"analyze":[3],"a":[4,26,37,112,133,142],"new":[5],"policy":[6,20,165],"gradient":[7,45],"algorithm":[8],"for":[9,70,132],"reinforcement":[10],"learning":[11],"(RL),":[12],"relative":[13,23],"Monte":[14],"Carlo":[15],"(rMC).":[16],"The":[17,43,74],"method":[18,75],"estimates":[19],"gradients":[21],"using":[22],"returns":[24],"between":[25],"root":[27],"sample":[28],"path":[29],"counterfactual":[31],"simulated":[32,83],"paths,":[33],"instantiated":[34],"by":[35],"taking":[36],"different":[38],"action":[39],"from":[40],"the":[41,82,90],"root.":[42],"resulting":[44],"estimate":[46],"is":[47,55,65,100],"both":[48],"unbiased":[49],"has":[51,128,163],"low":[52,130],"variance.":[53],"rMC":[54,155],"compatible":[56],"with":[57],"any":[58],"differentiable":[59],"policy,":[60],"including":[61],"neural":[62],"networks,":[63],"guaranteed":[66],"to":[67,85,104,151],"converge":[68],"even":[69],"infinite":[71],"horizon":[72],"tasks.":[73],"utilizes":[76],"common":[77],"random":[78],"number":[79],"coupling":[80],"of":[81,135],"paths":[84,93],"reduce":[86],"variance":[87],"increase":[89],"likelihood":[91],"that":[92,126,149],"merge,":[94],"thereby":[95],"reducing":[96],"simulation":[97],"complexity.":[98],"It":[99],"particularly":[101],"well":[102],"suited":[103],"discrete":[105],"event":[106],"control":[107,137],"problems":[108],"where":[109],"actions":[110],"have":[111],"\"local\"":[113],"effect,":[114],"such":[115],"as":[116],"queueing,":[117],"supply":[118],"chain,":[119],"or":[120],"ride-hailing":[121],"problems.":[122,138],"Indeed,":[123],"we":[124],"show":[125,148],"it":[127],"provably":[129],"complexity":[131],"family":[134],"inventory":[136,144],"Numerical":[139],"tests":[140],"on":[141],"challenging":[143],"fulfillment":[146],"problem":[147],"compared":[150],"traditional":[152],"RL":[153],"approaches,":[154],"converges":[156],"in":[157],"far":[158],"fewer":[159],"iterations":[160],"(lower":[161],"variance),":[162],"better":[164],"performance":[166],"(unbiased),":[167],"requires":[169],"minimal":[170],"hyperparameter":[171],"tuning.":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}