{"id":"https://openalex.org/W4385768230","doi":"https://doi.org/10.24963/ijcai.2023/505","title":"Explainable Reinforcement Learning via a Causal World Model","display_name":"Explainable Reinforcement Learning via a Causal World Model","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768230","doi":"https://doi.org/10.24963/ijcai.2023/505"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/505","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/505","pdf_url":"https://www.ijcai.org/proceedings/2023/0505.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second 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/2023/0505.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100560075","display_name":"Zhongwei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwei Yu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076546255","display_name":"Jingqing Ruan","orcid":"https://orcid.org/0000-0002-4857-9053"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqing Ruan","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences","Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101684094","display_name":"Dengpeng Xing","orcid":"https://orcid.org/0000-0002-8251-9118"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengpeng Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6106,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91737721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4540","last_page":"4548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9993000030517578,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9993000030517578,"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":0.9884999990463257,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9872000217437744,"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/causal-model","display_name":"Causal model","score":0.7769202589988708},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7412809729576111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262428998947144},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6995575428009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5820347666740417},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5429413914680481},{"id":"https://openalex.org/keywords/causal-analysis","display_name":"Causal analysis","score":0.5280970931053162},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.48849642276763916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4564831256866455},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.12289905548095703},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07962605357170105}],"concepts":[{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.7769202589988708},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7412809729576111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262428998947144},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6995575428009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5820347666740417},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5429413914680481},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.5280970931053162},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.48849642276763916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4564831256866455},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.12289905548095703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07962605357170105},{"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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/505","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/505","pdf_url":"https://www.ijcai.org/proceedings/2023/0505.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/505","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/505","pdf_url":"https://www.ijcai.org/proceedings/2023/0505.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G4102930997","display_name":null,"funder_award_id":"62073324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768230.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1767411471","https://openalex.org/W1787224781","https://openalex.org/W1983362322","https://openalex.org/W2486285194","https://openalex.org/W2616247523","https://openalex.org/W2623293810","https://openalex.org/W2736601468","https://openalex.org/W2743381431","https://openalex.org/W2765566013","https://openalex.org/W2803635400","https://openalex.org/W2807807246","https://openalex.org/W2907354314","https://openalex.org/W2920362155","https://openalex.org/W2962872206","https://openalex.org/W2963324077","https://openalex.org/W2965361505","https://openalex.org/W2975704836","https://openalex.org/W2979225831","https://openalex.org/W2995523160","https://openalex.org/W2998004401","https://openalex.org/W3006702859","https://openalex.org/W3007111659","https://openalex.org/W3011651653","https://openalex.org/W3012550998","https://openalex.org/W3036513508","https://openalex.org/W3081090156","https://openalex.org/W3082925502","https://openalex.org/W3098338892","https://openalex.org/W3102564565","https://openalex.org/W3103946812","https://openalex.org/W3125947392","https://openalex.org/W3147999658","https://openalex.org/W3185645972","https://openalex.org/W3206265976","https://openalex.org/W4238288653","https://openalex.org/W4283694818","https://openalex.org/W4283790357","https://openalex.org/W4286225098","https://openalex.org/W4287123726","https://openalex.org/W4287899998","https://openalex.org/W4288319859","https://openalex.org/W4288594419","https://openalex.org/W4294890823","https://openalex.org/W4295744821","https://openalex.org/W4298206671","https://openalex.org/W4367295663","https://openalex.org/W4394666657","https://openalex.org/W6752087564","https://openalex.org/W6791858558","https://openalex.org/W6864014924","https://openalex.org/W6864487941"],"related_works":["https://openalex.org/W2102962081","https://openalex.org/W2102630578","https://openalex.org/W1996752603","https://openalex.org/W2623890275","https://openalex.org/W1549106357","https://openalex.org/W2528529373","https://openalex.org/W1999181696","https://openalex.org/W2082218277","https://openalex.org/W4372338229","https://openalex.org/W1709350551"],"abstract_inverted_index":{"Generating":[0],"explanations":[1],"for":[2,25],"reinforcement":[3],"learning":[4,29],"(RL)":[5],"is":[6],"challenging":[7],"as":[8,109],"actions":[9,59,66],"may":[10],"produce":[11],"long-term":[12,56],"effects":[13,57],"on":[14],"the":[15,38,42,47,55,110],"future.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,101],"develop":[21],"a":[22,30,99],"novel":[23],"framework":[24],"explainable":[26],"RL":[27],"by":[28],"causal":[31,39,61,105],"world":[32],"model":[33,45,86,106],"without":[34],"prior":[35],"knowledge":[36],"of":[37,41,49,58],"structure":[40],"environment.":[43],"The":[44],"captures":[46],"influence":[48,67],"actions,":[50],"allowing":[51],"us":[52],"to":[53,73],"interpret":[54],"through":[60],"chains,":[62],"which":[63,80],"present":[64],"how":[65],"environmental":[68],"variables":[69],"and":[70,114],"finally":[71],"lead":[72],"rewards.":[74],"Different":[75],"from":[76,82],"most":[77],"explanatory":[78],"models":[79],"suffer":[81],"low":[83],"accuracy,":[84],"our":[85,104],"remains":[87],"accurate":[88],"while":[89],"improving":[90],"explainability,":[91],"making":[92],"it":[93],"applicable":[94],"in":[95],"model-based":[96],"learning.":[97,115],"As":[98],"result,":[100],"demonstrate":[102],"that":[103],"can":[107],"serve":[108],"bridge":[111],"between":[112],"explainability":[113]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}