{"id":"https://openalex.org/W7166096001","doi":"https://doi.org/10.5555/3709347.3743863","title":"Self-Interpretable Reinforcement Learning via Rule Ensembles","display_name":"Self-Interpretable Reinforcement Learning via Rule Ensembles","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7166096001","doi":"https://doi.org/10.5555/3709347.3743863"},"language":"en","primary_location":{"id":"pmh:oai:monash.edu:openaire/2e8b1627-769f-4cdf-881f-4023770441da","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/2e8b1627-769f-4cdf-881f-4023770441da","pdf_url":"https://researchmgt.monash.edu/ws/files/791161212/754101858-oa.pdf","source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://researchmgt.monash.edu/ws/files/791161212/754101858-oa.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100633319","display_name":"Yue Yang","orcid":"https://orcid.org/0000-0001-9002-9760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346596","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0001-6707-4344"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139403231","display_name":"Yu Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108646552","display_name":"H Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hao; id_orcid 0000-0001-5182-7938","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.927299976348877,"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":0.927299976348877,"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":0.01940000057220459,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8756999969482422},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.829800009727478},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4754999876022339},{"id":"https://openalex.org/keywords/learning-rule","display_name":"Learning rule","score":0.4708000123500824},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46230000257492065},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41769999265670776}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8756999969482422},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.829800009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6922000050544739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638000011444092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4754999876022339},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.4708000123500824},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.30149999260902405}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:monash.edu:openaire/2e8b1627-769f-4cdf-881f-4023770441da","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/2e8b1627-769f-4cdf-881f-4023770441da","pdf_url":"https://researchmgt.monash.edu/ws/files/791161212/754101858-oa.pdf","source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:monash.edu:openaire/2e8b1627-769f-4cdf-881f-4023770441da","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/2e8b1627-769f-4cdf-881f-4023770441da","pdf_url":"https://researchmgt.monash.edu/ws/files/791161212/754101858-oa.pdf","source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6453683972358704}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166096001.pdf","grobid_xml":"https://content.openalex.org/works/W7166096001.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"reinforcement":[1,73,112],"learning":[2,74,113],"(RL)":[3],"models,":[4],"often":[5],"functioning":[6],"as":[7,150],"complex":[8],"'black":[9],"boxes,'":[10],"obscure":[11],"decision-making":[12,53],"processes.":[13],"This":[14,87],"lack":[15],"of":[16,99,125,145],"transparency":[17],"limits":[18],"its":[19],"applicability":[20],"in":[21,72],"critical":[22],"real-world":[23],"applications":[24],"where":[25],"clear":[26],"reasoning":[27],"behind":[28],"algorithmic":[29],"choices":[30],"is":[31],"crucial.":[32],"To":[33],"tackle":[34],"this":[35],"issue,":[36],"we":[37],"suggest":[38],"moving":[39],"from":[40,130],"neural":[41],"network":[42],"or":[43,141],"tabular":[44],"approaches":[45],"to":[46,58,68,92,118],"a":[47,82,104],"rule":[48,66,84,108,126,138],"ensemble":[49],"model,":[50],"which":[51],"improves":[52],"clarity":[54],"and":[55,121,153,159],"adapts":[56],"dynamically":[57],"environmental":[59],"interactions.":[60],"Instead,":[61],"our":[62,136],"method":[63,88],"constructs":[64],"additive":[65],"ensembles":[67,109,139],"approximate":[69],"the":[70,90,97,111,123,143],"Q-value":[71],"using":[75],"orthogonal":[76],"gradient":[77],"boosting":[78],"(OGB)":[79],"combined":[80],"with":[81],"post-processing":[83],"replacement":[85],"technique.":[86],"enables":[89],"model":[91],"provide":[93],"inherent":[94],"explanations":[95],"through":[96],"use":[98],"rules.":[100],"Our":[101],"study":[102],"sets":[103],"theoretical":[105],"foundation":[106],"for":[107],"within":[110],"framework,":[114],"emphasizing":[115],"their":[116],"capacity":[117],"boost":[119],"interpretability":[120],"facilitate":[122],"analysis":[124],"impacts.":[127],"Experimental":[128],"results":[129],"seven":[131],"classic":[132],"environments":[133],"demonstrate":[134],"that":[135],"proposed":[137],"match":[140],"exceed":[142],"performance":[144],"representative":[146],"RL":[147],"models":[148],"such":[149],"DQN,":[151],"A2C,":[152],"PPO,":[154],"while":[155],"also":[156],"providing":[157],"self-interpretability":[158],"transparency.":[160]},"counts_by_year":[],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2026-06-27T00:00:00"}