{"id":"https://openalex.org/W7223386385","doi":"https://doi.org/10.1007/978-3-032-42348-1_3","title":"Explainable Variational Quantum Policy Gradient: SHAP-Based Interpretability of Quantum Reinforcement Learning Agents on CartPole","display_name":"Explainable Variational Quantum Policy Gradient: SHAP-Based Interpretability of Quantum Reinforcement Learning Agents on CartPole","publication_year":2026,"publication_date":"2026-10-23","ids":{"openalex":"https://openalex.org/W7223386385","doi":"https://doi.org/10.1007/978-3-032-42348-1_3"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-42348-1_3","doi":"https://doi.org/10.1007/978-3-032-42348-1_3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-42348-1_3","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7223411182","display_name":"Applied Intelligence and Informatics"},"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-032-42348-1_3","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061835853","display_name":"Sandeep Gupta","orcid":"https://orcid.org/0000-0002-2046-115X","observed_orcids":["https://orcid.org/0000-0002-2046-115X"]},"institutions":[{"id":"https://openalex.org/I159219196","display_name":"Rajasthan Technical University","ror":"https://ror.org/056bber35","country_code":"IN","type":"education","lineage":["https://openalex.org/I159219196"]},{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeep Gupta","raw_affiliation_strings":["Department of Electronics and Communication Engineering, Poornima College of Engineering (Affiliated to Rajasthan Technical University, Kota), Jaipur, 302022, Rajasthan, India","Department of Maritime Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, Gujarat, India"],"raw_orcid":"https://orcid.org/0000-0002-2046-115X","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, Poornima College of Engineering (Affiliated to Rajasthan Technical University, Kota), Jaipur, 302022, Rajasthan, India","institution_ids":["https://openalex.org/I159219196"]},{"raw_affiliation_string":"Department of Maritime Engineering, Indian Institute of Technology Gandhinagar, Gandhinagar, 382355, Gujarat, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103608739","display_name":"Sazzad Hossain","orcid":"https://orcid.org/0009-0003-1351-7287","observed_orcids":["https://orcid.org/0009-0003-1351-7287"]},"institutions":[{"id":"https://openalex.org/I1299170990","display_name":"Samarkand State University named after Sharof Rashidov","ror":"https://ror.org/02b6gy972","country_code":"UZ","type":"education","lineage":["https://openalex.org/I1299170990"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Sazzad Hossain","raw_affiliation_strings":["Department of System Management and Information Security, Samarkand State University, Samarkand, 140104, Uzbekistan"],"raw_orcid":"https://orcid.org/0009-0003-1351-7287","affiliations":[{"raw_affiliation_string":"Department of System Management and Information Security, Samarkand State University, Samarkand, 140104, Uzbekistan","institution_ids":["https://openalex.org/I1299170990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112960642","display_name":"Akmal Akhatov","orcid":"https://orcid.org/0000-0003-3834-854X","observed_orcids":["https://orcid.org/0000-0003-3834-854X"]},"institutions":[{"id":"https://openalex.org/I1299170990","display_name":"Samarkand State University named after Sharof Rashidov","ror":"https://ror.org/02b6gy972","country_code":"UZ","type":"education","lineage":["https://openalex.org/I1299170990"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Akmal Akhatov","raw_affiliation_strings":["Faculty of Artificial Intelligence and Digital Technologies, Samarkand State University, Samarkand, 140104, Uzbekistan"],"raw_orcid":"https://orcid.org/0000-0003-3834-854X","affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence and Digital Technologies, Samarkand State University, Samarkand, 140104, Uzbekistan","institution_ids":["https://openalex.org/I1299170990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096744794","display_name":"Mekhriddin Nurmamatov","orcid":"https://orcid.org/0000-0002-9619-5791","observed_orcids":["https://orcid.org/0000-0002-9619-5791"]},"institutions":[{"id":"https://openalex.org/I1299170990","display_name":"Samarkand State University named after Sharof Rashidov","ror":"https://ror.org/02b6gy972","country_code":"UZ","type":"education","lineage":["https://openalex.org/I1299170990"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Nurmamatov Mekhriddin","raw_affiliation_strings":["Department of System Management and Information Security, Samarkand State University, Samarkand, 140104, Uzbekistan"],"raw_orcid":"https://orcid.org/0000-0002-9619-5791","affiliations":[{"raw_affiliation_string":"Department of System Management and Information Security, Samarkand State University, Samarkand, 140104, Uzbekistan","institution_ids":["https://openalex.org/I1299170990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029628860","display_name":"Kanad Ray","orcid":"https://orcid.org/0000-0001-9324-2778","observed_orcids":["https://orcid.org/0000-0001-9324-2778"]},"institutions":[{"id":"https://openalex.org/I1299170990","display_name":"Samarkand State University named after Sharof Rashidov","ror":"https://ror.org/02b6gy972","country_code":"UZ","type":"education","lineage":["https://openalex.org/I1299170990"]},{"id":"https://openalex.org/I4405263076","display_name":"Amity University Jaipur","ror":"https://ror.org/027sha433","country_code":"IN","type":"education","lineage":["https://openalex.org/I191972202","https://openalex.org/I4405263076"]}],"countries":["IN","UZ"],"is_corresponding":true,"raw_author_name":"Kanad Ray","raw_affiliation_strings":["Amity Cognitive Computing and Brain Informatics Centre, Amity University Rajasthan, Jaipur, 303002, Rajasthan, India","Faculty of Artificial Intelligence and Digital Technologies, Samarkand State University, Samarkand, 140104, Uzbekistan"],"raw_orcid":"https://orcid.org/0000-0001-9324-2778","affiliations":[{"raw_affiliation_string":"Amity Cognitive Computing and Brain Informatics Centre, Amity University Rajasthan, Jaipur, 303002, Rajasthan, India","institution_ids":["https://openalex.org/I4405263076"]},{"raw_affiliation_string":"Faculty of Artificial Intelligence and Digital Technologies, Samarkand State University, Samarkand, 140104, Uzbekistan","institution_ids":["https://openalex.org/I1299170990"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029628860"],"corresponding_institution_ids":["https://openalex.org/I1299170990","https://openalex.org/I4405263076"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8198000192642212,"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":0.8198000192642212,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.17479999363422394,"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":0.0010999999940395355,"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/quantum-reinforcement-learning","display_name":"quantum reinforcement learning","score":0.8119999766349792},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.8949999809265137},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.8920000195503235},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.7099999785423279},{"id":"https://openalex.org/keywords/cartpole","display_name":"CartPole","score":0.7720000147819519},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"inverted pendulum","score":0.7799999713897705},{"id":"https://openalex.org/keywords/hybrid-quantum-classical-neural-networks","display_name":"hybrid quantum-classical neural networks","score":0.6809999942779541},{"id":"https://openalex.org/keywords/attribution","display_name":"attribution","score":0.5059999823570251},{"id":"https://openalex.org/keywords/deep-q-network-comparison","display_name":"deep Q-network comparison","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9430999755859375},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434000134468079},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5785999894142151},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C137019171","wikidata":"https://www.wikidata.org/wiki/Q2623817","display_name":"Quantum algorithm","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C2778926657","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum system","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-42348-1_3","doi":"https://doi.org/10.1007/978-3-032-42348-1_3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-42348-1_3","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-42348-1_3","doi":"https://doi.org/10.1007/978-3-032-42348-1_3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-42348-1_3","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1568345435","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2521267242","https://openalex.org/W2781738013","https://openalex.org/W2790388700","https://openalex.org/W2792315573","https://openalex.org/W2794444783","https://openalex.org/W2798434869","https://openalex.org/W2903221501","https://openalex.org/W2911423727","https://openalex.org/W2954939433","https://openalex.org/W2980446414","https://openalex.org/W3088409280","https://openalex.org/W3093944484","https://openalex.org/W3111162498","https://openalex.org/W3126329527","https://openalex.org/W3141755656","https://openalex.org/W4285301343","https://openalex.org/W4364377871","https://openalex.org/W6968906521","https://openalex.org/W7163898985","https://openalex.org/W7168164945","https://openalex.org/W7204172323"],"related_works":["https://openalex.org/W7203650148","https://openalex.org/W4364377871","https://openalex.org/W7133325949","https://openalex.org/W3134744093","https://openalex.org/W7053180609","https://openalex.org/W4416874942","https://openalex.org/W7155590144","https://openalex.org/W3141755656","https://openalex.org/W7024372049","https://openalex.org/W4293051376"],"abstract_inverted_index":{"The":[0,165],"decisions":[1],"of":[2,21,53,134,141,156],"variational":[3],"quantum":[4,157],"reinforcement":[5],"learning":[6],"agents":[7],"remain":[8],"largely":[9],"opaque,":[10],"limiting":[11],"trust":[12],"in":[13,159],"safety-critical":[14],"deployments.":[15],"We":[16,144],"present":[17],"the":[18,98,111,139,142,160],"first":[19],"application":[20],"SHapley":[22],"Additive":[23],"exPlanations":[24],"(SHAP)":[25],"to":[26,64],"a":[27,49,69,83],"Variational":[28],"Quantum":[29],"Policy":[30],"Gradient":[31],"(VQPG)":[32],"agent":[33],"trained":[34],"on":[35,171],"CartPole-v1.":[36],"Our":[37],"4-qubit":[38],"hybrid":[39],"quantum-classical":[40],"policy":[41],"uses":[42],"only":[43],"46":[44],"trainable":[45],"parameters":[46,77],"and":[47,78],"achieves":[48],"mean":[50],"evaluation":[51],"score":[52],"$$496.4":[54],"\\pm":[55,66,80],"8.1$$":[56],"over":[57],"ten":[58],"independent":[59],"seeds":[60],"(maximum":[61],"500.0),":[62],"compared":[63],"$$249.7":[65],"38.6$$":[67],"for":[68,82,119],"standard":[70],"Deep":[71],"Q-Network":[72],"(DQN)":[73],"with":[74,115],"9":[75],"220":[76],"$$412.3":[79],"67.9$$":[81],"parameter-matched":[84],"Tiny-MLP":[85],"(30":[86],"parameters,":[87],"identical":[88],"training":[89],"budget).":[90],"SHAP":[91],"analysis":[92],"identifies":[93],"Pole":[94],"Angular":[95],"Velocity":[96],"as":[97],"dominant":[99],"decision":[100],"feature":[101],"(mean":[102],"$$|\\phi":[103],"|":[104],"=":[105],"0.2859$$":[106],",":[107],"approximately":[108],"$$7\\times":[109],"$$":[110],"next":[112],"feature),":[113],"consistent":[114],"classical":[116],"control":[117],"theory":[118],"inverted":[120],"pendulum":[121],"stabilisation.":[122],"This":[123],"attribution":[124],"is":[125,163,169],"stable":[126],"across":[127],"five":[128],"independently":[129],"sampled":[130],"background":[131],"sets":[132],"(coefficient":[133],"variation":[135],"$$3.1\\%$$":[136],"),":[137],"confirming":[138],"reliability":[140],"explanation.":[143],"emphasise":[145],"that":[146],"all":[147],"results":[148],"are":[149],"obtained":[150],"under":[151,173],"noiseless":[152],"simulation;":[153],"no":[154],"claim":[155],"advantage":[158],"complexity-theoretic":[161],"sense":[162],"made.":[164],"complete":[166],"experimental":[167],"package":[168],"deposited":[170],"https://zenodo.org/":[172],"CC-BY":[174],"4.0.":[175]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-24T00:00:00"}
