{"id":"https://openalex.org/W4392903738","doi":"https://doi.org/10.1109/icassp48485.2024.10446037","title":"Interpretable Policy Extraction with Neuro-Symbolic Reinforcement Learning","display_name":"Interpretable Policy Extraction with Neuro-Symbolic Reinforcement Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903738","doi":"https://doi.org/10.1109/icassp48485.2024.10446037"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000393142","display_name":"Rajdeep Dutta","orcid":"https://orcid.org/0000-0003-0195-2153"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Rajdeep Dutta","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research (I2R)","Institute for Infocomm Research (I2R), A*STAR"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102631468","display_name":"Qincheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qincheng Wang","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064539777","display_name":"Ankur Singh","orcid":"https://orcid.org/0000-0003-1336-6493"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ankur Singh","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research (I2R)","Institute for Infocomm Research (I2R), A*STAR"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091952725","display_name":"Dhruv Kumarjiguda","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dhruv Kumarjiguda","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418684","display_name":"Xiaoli Li","orcid":"https://orcid.org/0000-0002-0762-6562"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li Xiaoli","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research (I2R)","Institute for Infocomm Research (I2R), A*STAR"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083824197","display_name":"J. Senthilnath","orcid":"https://orcid.org/0000-0002-1737-7985"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Senthilnath Jayavelu","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research (I2R)","Institute for Infocomm Research (I2R), A*STAR"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000393142"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.6813,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72515615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7570","last_page":"7574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T10320","display_name":"Neural Networks and Applications","score":0.993399977684021,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9901000261306763,"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":0.9080784916877747},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8182922601699829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7626538872718811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6313024163246155},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.563322126865387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5489984154701233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5478789210319519},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.520354688167572},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48920774459838867},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47624969482421875},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.45809608697891235}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9080784916877747},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8182922601699829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626538872718811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6313024163246155},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.563322126865387},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5489984154701233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5478789210319519},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.520354688167572},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48920774459838867},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47624969482421875},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.45809608697891235},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8387079393","display_name":null,"funder_award_id":"A1898b0043","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2015731569","https://openalex.org/W2492794003","https://openalex.org/W2539402368","https://openalex.org/W2570076534","https://openalex.org/W2596585349","https://openalex.org/W2773987374","https://openalex.org/W2902907165","https://openalex.org/W2963672746","https://openalex.org/W3016401366","https://openalex.org/W3100751385","https://openalex.org/W3206768895","https://openalex.org/W4223453145","https://openalex.org/W4241811150","https://openalex.org/W4307001524","https://openalex.org/W4372267540","https://openalex.org/W6675999342","https://openalex.org/W6683204974","https://openalex.org/W6684017535","https://openalex.org/W6704571135","https://openalex.org/W6796097400","https://openalex.org/W7046505727"],"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/W2894289927"],"abstract_inverted_index":{"This":[0,110],"paper":[1],"presents":[2],"a":[3,124],"novel":[4],"RL":[5],"algorithm,":[6],"S-REINFORCE,":[7],"designed":[8],"by":[9,91],"leveraging":[10,92],"two":[11],"types":[12],"of":[13,68,96],"function":[14],"approximators,":[15],"namely":[16],"Neural":[17],"Network":[18],"(NN)":[19],"and":[20,27,45,80,98,108,121],"Symbolic":[21],"Regressor":[22],"(SR),":[23],"to":[24,57],"produce":[25],"numerical":[26],"symbolic":[28,36,49],"policies":[29,102],"for":[30,116],"dynamic":[31,75],"decision-making":[32,76],"tasks,":[33],"respectively.":[34],"A":[35],"policy":[37,50],"uncovers":[38],"functional":[39],"relations":[40],"between":[41],"the":[42,48,59,63,93],"underlying":[43],"states":[44],"action-probabilities.":[46],"Further,":[47],"is":[51],"utilized":[52],"through":[53],"importance":[54],"sampling":[55],"(IS)":[56],"improve":[58],"rewards":[60],"received":[61],"during":[62],"learning":[64],"process.":[65],"The":[66,85],"effectiveness":[67],"S-REINFORCE":[69,100,112],"has":[70],"been":[71],"validated":[72],"on":[73],"various":[74],"problems":[77],"involving":[78],"low":[79],"high":[81],"dimensional":[82],"action":[83],"spaces.":[84],"results":[86],"obtained":[87],"clearly":[88],"demonstrate":[89],"that":[90,103],"complementary":[94],"strengths":[95],"NN":[97],"SR,":[99],"generates":[101],"exhibit":[104],"both":[105],"good":[106],"performance":[107],"interpretability.":[109],"makes":[111],"an":[113],"excellent":[114],"choice":[115],"real-world":[117],"applications":[118],"where":[119],"transparency":[120],"causality":[122],"play":[123],"crucial":[125],"role.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}