{"id":"https://openalex.org/W4403487424","doi":"https://doi.org/10.3233/faia240797","title":"Reduce, Reuse, Recycle: Categories for\u00a0Compositional\u00a0Reinforcement Learning","display_name":"Reduce, Reuse, Recycle: Categories for\u00a0Compositional\u00a0Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487424","doi":"https://doi.org/10.3233/faia240797"},"language":"en","primary_location":{"id":"doi:10.3233/faia240797","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240797","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240797","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240797","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080758702","display_name":"Georgios Bakirtzis","orcid":"https://orcid.org/0000-0003-4992-0193"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Georgios Bakirtzis","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":"https://orcid.org/0000-0003-4992-0193","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014583822","display_name":"Michail Savvas","orcid":"https://orcid.org/0000-0003-1437-7899"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michail Savvas","raw_affiliation_strings":["The University of Iowa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Iowa","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006249302","display_name":"Ruihan Zhao","orcid":"https://orcid.org/0009-0009-8208-0377"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruihan Zhao","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024120306","display_name":"Sandeep Chinchali","orcid":"https://orcid.org/0000-0002-0601-3633"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Chinchali","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080758702"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":6.2242,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96573544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"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/T14143","display_name":"Economic and Technological Innovation","score":0.1225999966263771,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14143","display_name":"Economic and Technological Innovation","score":0.1225999966263771,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8490338325500488},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6991298198699951},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6189653277397156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4546546936035156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2850778102874756},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2606944441795349},{"id":"https://openalex.org/keywords/waste-management","display_name":"Waste management","score":0.19145503640174866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1746029257774353},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12067702412605286}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8490338325500488},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6991298198699951},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6189653277397156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4546546936035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2850778102874756},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2606944441795349},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.19145503640174866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1746029257774353},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12067702412605286}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240797","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240797","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240797","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240797","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240797","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240797","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403487424.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0],"reinforcement":[1,36,118],"learning,":[2],"conducting":[3],"task":[4,59,67],"composition":[5,68],"by":[6,120],"forming":[7],"cohesive,":[8],"executable":[9],"sequences":[10],"from":[11],"multiple":[12],"tasks":[13,21,92],"remains":[14],"challenging.":[15],"However,":[16],"the":[17,43,47,70,114],"ability":[18],"to":[19],"(de)compose":[20],"is":[22,38],"a":[23],"linchpin":[24],"in":[25],"developing":[26],"robotic":[27,130],"systems":[28],"capable":[29],"of":[30,46,51,55,72,86,100,117],"learning":[31,37,119,128],"complex":[32,91,129],"behaviors.":[33],"Yet,":[34],"compositional":[35,81],"beset":[39],"with":[40],"difficulties,":[41],"including":[42],"high":[44],"dimensionality":[45],"problem":[48],"space,":[49],"scarcity":[50],"rewards,":[52],"and":[53,79,107,125],"absence":[54],"system":[56,109],"robustness":[57],"after":[58],"composition.":[60],"To":[61],"surmount":[62],"these":[63],"challenges,":[64],"we":[65],"view":[66],"through":[69],"prism":[71],"category":[73],"theory\u2014a":[74],"mathematical":[75],"discipline":[76],"exploring":[77],"structures":[78],"their":[80],"relationships.":[82],"The":[83],"categorical":[84,115],"properties":[85],"Markov":[87],"decision":[88],"processes":[89],"untangle":[90],"into":[93],"manageable":[94],"sub-tasks,":[95],"allowing":[96],"for":[97],"strategical":[98],"reduction":[99],"dimensionality,":[101],"facilitating":[102],"more":[103],"tractable":[104],"reward":[105],"structures,":[106],"bolstering":[108],"robustness.":[110],"Experimental":[111],"results":[112],"support":[113],"theory":[116],"enabling":[121],"skill":[122],"reduction,":[123],"reuse,":[124],"recycling":[126],"when":[127],"arm":[131],"tasks.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
