{"id":"https://openalex.org/W3191081139","doi":"https://doi.org/10.24963/ijcai.2021/268","title":"Inferring Time-delayed Causal Relations in POMDPs from the Principle of Independence of Cause and Mechanism","display_name":"Inferring Time-delayed Causal Relations in POMDPs from the Principle of Independence of Cause and Mechanism","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3191081139","doi":"https://doi.org/10.24963/ijcai.2021/268","mag":"3191081139"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/268","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/268","pdf_url":"https://www.ijcai.org/proceedings/2021/0268.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0268.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040549956","display_name":"Junchi Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junchi Liang","raw_affiliation_strings":["Department of Computer Science, Rutgers University, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068615270","display_name":"Abdeslam Boularias","orcid":"https://orcid.org/0000-0002-5587-4560"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdeslam Boularias","raw_affiliation_strings":["Department of Computer Science, Rutgers University, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4197,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69449992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1944","last_page":"1950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9580000042915344,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9204000234603882,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6975197792053223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6886669993400574},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.6645058393478394},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.5842711925506592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655497312545776},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5442460179328918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5027916431427002},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.4888388514518738},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43682754039764404},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3315034508705139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16586634516716003},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10039576888084412}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6975197792053223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886669993400574},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.6645058393478394},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.5842711925506592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655497312545776},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5442460179328918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5027916431427002},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4888388514518738},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43682754039764404},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3315034508705139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16586634516716003},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10039576888084412}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/268","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/268","pdf_url":"https://www.ijcai.org/proceedings/2021/0268.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/268","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/268","pdf_url":"https://www.ijcai.org/proceedings/2021/0268.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2006546336","display_name":"NRI: INT: COLLAB: Integrated Modeling and Learning for Robust Grasping and Dexterous Manipulation with Adaptive Hands","funder_award_id":"1734492","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4056661646","display_name":"RI: CAREER: Task-Oriented Model Identification for Robust Robotic Manipulation","funder_award_id":"1846043","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191081139.pdf","grobid_xml":"https://content.openalex.org/works/W3191081139.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1482778976","https://openalex.org/W1540337045","https://openalex.org/W1589170661","https://openalex.org/W2098661970","https://openalex.org/W2101355568","https://openalex.org/W2118688707","https://openalex.org/W2122458975","https://openalex.org/W2141690016","https://openalex.org/W2518713116","https://openalex.org/W2528489519","https://openalex.org/W2569188995","https://openalex.org/W2606047872","https://openalex.org/W2624780181","https://openalex.org/W2786344118","https://openalex.org/W2787365188","https://openalex.org/W2900152462","https://openalex.org/W2952902960","https://openalex.org/W2952915411","https://openalex.org/W2962824919","https://openalex.org/W2963403868","https://openalex.org/W2963634205","https://openalex.org/W2963871073","https://openalex.org/W4212861043","https://openalex.org/W4289294484","https://openalex.org/W4293862243","https://openalex.org/W4298857966","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W3136325136"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2,49],"an":[3],"algorithm":[4,39],"for":[5,131],"discovering":[6],"implicit":[7],"and":[8,29,47,55,90,105,119,136,140],"delayed":[9],"causal":[10,101],"relations":[11],"between":[12,88,103],"events":[13,76,104],"observed":[14],"by":[15,80],"a":[16,100,126],"robot":[17],"at":[18],"regular":[19],"or":[20],"arbitrary":[21],"times,":[22],"with":[23,43],"the":[24,44,57,60,108,141],"objective":[25],"of":[26,31,59,71,86],"improving":[27],"data-efficiency":[28],"interpretability":[30],"model-based":[32],"reinforcement":[33],"learning":[34],"(RL)":[35],"techniques.":[36,155],"The":[37,62,116],"proposed":[38],"initially":[40],"predicts":[41],"observations":[42],"Markov":[45],"assumption,":[46],"incrementally":[48],"new":[50],"hidden":[51,63],"variables":[52,64],"to":[53,94,113],"explain":[54],"reduce":[56],"stochasticity":[58],"observations.":[61],"are":[65,77,122],"memory":[66],"units":[67],"that":[68,147],"keep":[69],"track":[70],"pertinent":[72],"past":[73],"events.":[74],"Such":[75],"systematically":[78],"identified":[79],"their":[81],"information":[82,109],"gains.":[83],"A":[84],"test":[85],"independence":[87],"inputs":[89],"mechanisms":[91],"is":[92,99,111],"performed":[93],"identify":[95],"cases":[96],"when":[97,107],"there":[98],"link":[102],"those":[106],"gain":[110],"due":[112],"confounding":[114],"variables.":[115],"learned":[117],"transition":[118],"reward":[120],"models":[121],"then":[123],"used":[124],"in":[125],"Monte":[127],"Carlo":[128],"tree":[129],"search":[130],"planning.":[132],"Experiments":[133],"on":[134],"simulated":[135],"real":[137],"robotic":[138],"tasks,":[139],"challenging":[142],"3D":[143],"game":[144],"Doom":[145],"show":[146],"this":[148],"method":[149],"significantly":[150],"improves":[151],"over":[152],"current":[153],"RL":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}