{"id":"https://openalex.org/W4402260386","doi":"https://doi.org/10.23919/acc60939.2024.10644503","title":"Counterfactually-Guided Causal Reinforcement Learning with Reward Machines","display_name":"Counterfactually-Guided Causal Reinforcement Learning with Reward Machines","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402260386","doi":"https://doi.org/10.23919/acc60939.2024.10644503"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644503","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5065122789","display_name":"Nasim Baharisangari","orcid":"https://orcid.org/0000-0002-3984-8733"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nasim Baharisangari","raw_affiliation_strings":["School for Engineering of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092346339","display_name":"Yash Paliwal","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yash Paliwal","raw_affiliation_strings":["School for Engineering of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013789785","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0002-0440-0912"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Xu","raw_affiliation_strings":["School for Engineering of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School for Engineering of Matter, Transport and Energy, Arizona State University,Tempe,AZ,85287","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065122789"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.3193,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64823933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"522","last_page":"527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9973000288009644,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9973000288009644,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9932000041007996,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.7482709288597107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6706295609474182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4909403622150421},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3865463435649872}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7482709288597107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6706295609474182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909403622150421},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3865463435649872}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644503","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc60939.2024.10644503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1864718896","display_name":null,"funder_award_id":"CNS 2304863,CNS 2339774,ONR N00014-23-1-2505","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2746553466","https://openalex.org/W2956149426","https://openalex.org/W2970673985","https://openalex.org/W2972500268","https://openalex.org/W3181291875","https://openalex.org/W4289288202","https://openalex.org/W4298857966","https://openalex.org/W4385462630","https://openalex.org/W6638088447","https://openalex.org/W6682205418","https://openalex.org/W6742245242","https://openalex.org/W6752298494","https://openalex.org/W6765905676","https://openalex.org/W6780369355","https://openalex.org/W6797910908"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0,28,49],"causal":[1],"reinforcement":[2,36],"learning":[3,37],"(RL),":[4],"counterfactual":[5,33,59,78,98],"reasoning":[6,34],"deals":[7],"with":[8,45,61,76,108,122],"\u201cwhat":[9],"if\u201d":[10],"situations":[11],"and":[12,35,39,118],"allows":[13],"for":[14],"investigating":[15],"the":[16,57,62,77,82,93,97,102,120,131],"potential":[17],"consequences":[18],"of":[19,65],"actions":[20],"or":[21],"events":[22],"that":[23,128],"did":[24],"not":[25],"actually":[26],"happen.":[27],"this":[29],"paper,":[30],"we":[31,54,71,111],"combine":[32],"(RL)":[38],"propose":[40],"Counterfactually-Guided":[41],"Causal":[42],"Reinforcement":[43],"Learning":[44],"Reward":[46],"Machines":[47],"(CGC-RL).":[48],"CGC-RL,":[50],"using":[51],"observational":[52],"data,":[53],"first":[55],"compute":[56],"optimal":[58],"sequence":[60],"highest":[63],"probability":[64],"completing":[66],"a":[67],"given":[68],"task.":[69],"Then,":[70],"construct":[72],"an":[73],"RM":[74,84],"compatible":[75],"sequence.":[79,99],"We":[80,100],"use":[81],"constructed":[83],"to":[85,91,95],"apply":[86],"dynamic":[87,105],"potential-based":[88],"reward":[89,106],"shaping":[90,107],"encourage":[92],"agent":[94],"follow":[96],"prove":[101],"policy-invariance":[103],"under":[104],"RMs.":[109],"Finally,":[110],"implement":[112],"CGC-RL":[113,129],"in":[114],"one":[115],"case":[116],"study":[117],"compare":[119],"results":[121,126],"three":[123],"baselines.":[124,132],"Our":[125],"show":[127],"outperforms":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}