{"id":"https://openalex.org/W4416213818","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228766","title":"Causality-Guided Policy Optimization in Reinforcement Learning","display_name":"Causality-Guided Policy Optimization in Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416213818","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228766"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101518967","display_name":"Lishan Yang","orcid":"https://orcid.org/0000-0002-3691-7377"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lishan Yang","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071745646","display_name":"Q. Chen","orcid":"https://orcid.org/0009-0001-2859-2488"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuju Chen","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007692391","display_name":"Lihua Liu","orcid":"https://orcid.org/0000-0002-5774-951X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I79305253","display_name":"National Defence University","ror":"https://ror.org/045vxh980","country_code":"PK","type":"education","lineage":["https://openalex.org/I79305253"]}],"countries":["CN","PK"],"is_corresponding":false,"raw_author_name":"Lihua Liu","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defence Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defence Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575","https://openalex.org/I79305253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021274571","display_name":"Yibin Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zhan","raw_affiliation_strings":["JD Explore Academy,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Explore Academy,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31790663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.602400004863739,"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":0.602400004863739,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.03189999982714653,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.02199999988079071,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8549000024795532},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7495999932289124},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5056999921798706},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4562000036239624},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.39730000495910645},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37070000171661377},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.3325999975204468},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8549000024795532},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7495999932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6039000153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113999843597412},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C12298181","wikidata":"https://www.wikidata.org/wiki/Q7246814","display_name":"Proactive learning","level":5,"score":0.3061999976634979},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.25130000710487366},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2877093712","https://openalex.org/W2885282028","https://openalex.org/W2982316857","https://openalex.org/W3100366369","https://openalex.org/W3100789280","https://openalex.org/W3175558129","https://openalex.org/W3195433036","https://openalex.org/W3216656735","https://openalex.org/W4206988054","https://openalex.org/W4295046496","https://openalex.org/W4312055489","https://openalex.org/W4388543772"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning,":[1,7],"a":[2,61,95],"prominent":[3],"area":[4],"in":[5,9,44,56,69,88,134,137,151,162],"machine":[6],"excels":[8],"executing":[10],"complex":[11,90,159],"tasks":[12],"by":[13,113,155],"learning":[14,38,77,98,127,167],"strategies":[15],"through":[16],"environmental":[17,51],"interaction.":[18],"Its":[19],"unique":[20],"capability":[21],"to":[22,63],"operate":[23],"without":[24],"explicit":[25],"guidance":[26],"places":[27],"it":[28],"at":[29],"the":[30,70,76,82,106,126],"forefront":[31],"of":[32,85,147],"advancing":[33],"autonomous":[34],"systems.":[35],"Traditional":[36],"reinforcement":[37,97,163],"approaches,":[39],"however,":[40],"face":[41],"substantial":[42],"challenges":[43,153],"scenarios":[45],"with":[46],"sparse":[47,156],"rewards":[48,157],"and":[49,60,65,121,143,158,169,177],"intricate":[50],"elements.":[52],"These":[53],"limitations":[54],"manifest":[55],"low":[57],"sample":[58],"efficiency":[59,78,168],"struggle":[62],"discern":[64],"leverage":[66],"causal":[67,103,115,132,160],"structures":[68,161],"environment.":[71],"This":[72,92],"not":[73],"only":[74],"impedes":[75],"but":[79],"also":[80,173],"restricts":[81],"broader":[83],"application":[84],"these":[86],"models":[87],"more":[89,138],"scenarios.":[91],"study":[93],"introduces":[94],"causality-driven":[96],"(CDRL)":[99],"framework,":[100],"that":[101],"infuses":[102],"knowledge":[104],"into":[105],"actor-critic":[107],"model.":[108],"It":[109,165],"enhances":[110],"strategic":[111,170],"accuracy":[112],"using":[114],"insights":[116],"for":[117],"smarter":[118],"action":[119,141],"choices":[120],"state":[122],"evaluations,":[123],"thus":[124],"streamlining":[125],"process.":[128],"The":[129,145],"focus":[130],"on":[131],"relationships":[133],"CDRL":[135,148],"aids":[136],"accurate":[139],"future":[140],"predictions":[142],"decisions.":[144],"methodology":[146],"proves":[149],"effective":[150],"overcoming":[152],"posed":[154],"learning.":[164],"elevates":[166],"precision":[171],"while":[172],"improving":[174],"decision-making":[175],"transparency":[176],"interpretability.":[178]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}