{"id":"https://openalex.org/W4313491937","doi":"https://doi.org/10.1145/3570991.3571031","title":"Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning","display_name":"Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313491937","doi":"https://doi.org/10.1145/3570991.3571031"},"language":"en","primary_location":{"id":"doi:10.1145/3570991.3571031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th 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/A5045214135","display_name":"Harshad Khadilkar","orcid":"https://orcid.org/0000-0003-3601-778X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Harshad Khadilkar","raw_affiliation_strings":["Tata Consultancy Services Ltd, India"],"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Ltd, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028455101","display_name":"Hardik Meisheri","orcid":"https://orcid.org/0000-0002-9014-1098"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik Meisheri","raw_affiliation_strings":["Tata Consultancy Services Ltd, India"],"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Ltd, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045214135"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0027958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9595000147819519,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9524000287055969,"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":0.8861761689186096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7154657244682312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5941236019134521},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5190382599830627},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5139655470848083},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.502638578414917},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4763120412826538},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45426127314567566},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44758808612823486},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12760058045387268},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12552785873413086},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10162729024887085}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8861761689186096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7154657244682312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5941236019134521},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5190382599830627},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5139655470848083},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.502638578414917},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4763120412826538},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45426127314567566},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44758808612823486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12760058045387268},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12552785873413086},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10162729024887085},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570991.3571031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1569296262","https://openalex.org/W2107297861","https://openalex.org/W2145339207","https://openalex.org/W2998004401","https://openalex.org/W3083860260","https://openalex.org/W3166342932","https://openalex.org/W3173555766","https://openalex.org/W4287117686","https://openalex.org/W4287123726","https://openalex.org/W6771807793"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"A":[0],"significant":[1,44],"challenge":[2],"in":[3,46,52],"reinforcement":[4,129],"learning":[5,123,130],"is":[6,100],"quantifying":[7],"the":[8,64],"complex":[9],"relationship":[10],"between":[11],"actions":[12],"and":[13,63],"long-term":[14],"rewards.":[15,54],"The":[16],"effects":[17],"may":[18],"manifest":[19],"themselves":[20],"over":[21],"a":[22,38,71,85,119],"long":[23],"sequence":[24],"of":[25,122],"state-action":[26,66],"pairs,":[27],"making":[28],"them":[29],"hard":[30],"to":[31,40,70,82,102],"pinpoint.":[32],"In":[33,75],"this":[34,93],"paper,":[35],"we":[36,77],"propose":[37],"method":[39],"link":[41],"transitions":[42,56,83],"with":[43,48,89],"deviations":[45],"state":[47,87],"unusually":[49],"large":[50],"variations":[51],"subsequent":[53],"Such":[55],"are":[57,68],"marked":[58],"as":[59],"possible":[60],"causal":[61],"effects,":[62],"corresponding":[65,81],"pairs":[67],"added":[69],"separate":[72],"replay":[73],"buffer.":[74],"addition,":[76],"include":[78],"contrastive":[79],"samples":[80],"from":[84],"similar":[86],"but":[88],"differing":[90],"actions.":[91],"Including":[92],"Contrastive":[94],"Experience":[95],"Replay":[96],"(CER)":[97],"during":[98],"training":[99],"shown":[101],"outperform":[103],"standard":[104],"value-based":[105],"methods":[106],"on":[107],"2D":[108],"navigation":[109],"tasks.":[110],"We":[111],"believe":[112],"that":[113],"CER":[114],"can":[115],"be":[116],"useful":[117],"for":[118,126],"broad":[120],"class":[121],"tasks,":[124],"including":[125],"any":[127],"off-policy":[128],"algorithm.":[131]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}