{"id":"https://openalex.org/W4414402368","doi":"https://doi.org/10.4204/eptcs.429.15","title":"Reinforcement Learning in Categorical Cybernetics","display_name":"Reinforcement Learning in Categorical Cybernetics","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414402368","doi":"https://doi.org/10.4204/eptcs.429.15"},"language":"en","primary_location":{"id":"doi:10.4204/eptcs.429.15","is_oa":true,"landing_page_url":"https://doi.org/10.4204/eptcs.429.15","pdf_url":"https://eptcs.web.cse.unsw.edu.au/paper.cgi?ACT2024.15.pdf","source":{"id":"https://openalex.org/S4210216316","display_name":"Electronic Proceedings in Theoretical Computer Science","issn_l":"2075-2180","issn":["2075-2180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318029","host_organization_name":"Open Publishing Association","host_organization_lineage":["https://openalex.org/P4310318029"],"host_organization_lineage_names":["Open Publishing Association"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Proceedings in Theoretical Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://eptcs.web.cse.unsw.edu.au/paper.cgi?ACT2024.15.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085985351","display_name":"Jules Hedges","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jules Hedges","raw_affiliation_strings":["University of Strathclyde"],"affiliations":[{"raw_affiliation_string":"University of Strathclyde","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022815383","display_name":"Riu Rodr\u00edguez Sakamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Riu Rodr\u00edguez Sakamoto","raw_affiliation_strings":["University of Strathclyde"],"affiliations":[{"raw_affiliation_string":"University of Strathclyde","institution_ids":["https://openalex.org/I181647926"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085985351"],"corresponding_institution_ids":["https://openalex.org/I181647926"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3373543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"429","issue":null,"first_page":"270","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.6317999958992004,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.6317999958992004,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7412999868392944},{"id":"https://openalex.org/keywords/cybernetics","display_name":"Cybernetics","score":0.7013000249862671},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5672000050544739},{"id":"https://openalex.org/keywords/covariance-and-contravariance-of-vectors","display_name":"Covariance and contravariance of vectors","score":0.5322999954223633},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5066999793052673},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.42179998755455017}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7412999868392944},{"id":"https://openalex.org/C115286129","wikidata":"https://www.wikidata.org/wiki/Q123637","display_name":"Cybernetics","level":2,"score":0.7013000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5946000218391418},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595999956130981},{"id":"https://openalex.org/C206236147","wikidata":"https://www.wikidata.org/wiki/Q3555165","display_name":"Covariance and contravariance of vectors","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3878999948501587},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28060001134872437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4204/eptcs.429.15","is_oa":true,"landing_page_url":"https://doi.org/10.4204/eptcs.429.15","pdf_url":"https://eptcs.web.cse.unsw.edu.au/paper.cgi?ACT2024.15.pdf","source":{"id":"https://openalex.org/S4210216316","display_name":"Electronic Proceedings in Theoretical Computer Science","issn_l":"2075-2180","issn":["2075-2180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318029","host_organization_name":"Open Publishing Association","host_organization_lineage":["https://openalex.org/P4310318029"],"host_organization_lineage_names":["Open Publishing Association"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Proceedings in Theoretical Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4204/eptcs.429.15","is_oa":true,"landing_page_url":"https://doi.org/10.4204/eptcs.429.15","pdf_url":"https://eptcs.web.cse.unsw.edu.au/paper.cgi?ACT2024.15.pdf","source":{"id":"https://openalex.org/S4210216316","display_name":"Electronic Proceedings in Theoretical Computer Science","issn_l":"2075-2180","issn":["2075-2180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318029","host_organization_name":"Open Publishing Association","host_organization_lineage":["https://openalex.org/P4310318029"],"host_organization_lineage_names":["Open Publishing Association"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Proceedings in Theoretical Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414402368.pdf","grobid_xml":"https://content.openalex.org/works/W4414402368.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1520174560","https://openalex.org/W1572231946","https://openalex.org/W1694134801","https://openalex.org/W1976985540","https://openalex.org/W2071391326","https://openalex.org/W2107726111","https://openalex.org/W2119380668","https://openalex.org/W2766447205","https://openalex.org/W2941243118","https://openalex.org/W2964300838","https://openalex.org/W2969875089","https://openalex.org/W2982316857","https://openalex.org/W3001712757","https://openalex.org/W3092707305","https://openalex.org/W3104824432","https://openalex.org/W3114375010","https://openalex.org/W3134406394","https://openalex.org/W3160160563","https://openalex.org/W3164005523","https://openalex.org/W4289856129","https://openalex.org/W4299493806","https://openalex.org/W4301373598","https://openalex.org/W4376167346","https://openalex.org/W4385342861","https://openalex.org/W4385342938"],"related_works":[],"abstract_inverted_index":{"We":[0,55,73],"show":[1,32],"that":[2,17,33,63,83,99,166,175],"several":[3],"major":[4,133],"algorithms":[5,136],"of":[6,14,46,95,125,131,135,146],"reinforcement":[7],"learning":[8],"(RL)":[9],"fit":[10],"into":[11],"the":[12,47,57,85,92,101,126,132,187],"framework":[13],"categorical":[15],"cybernetics,":[16],"is":[18,169],"to":[19,60,65,182],"say,":[20],"parametrised":[21,61,81,89,97,111],"bidirectional":[22],"processes.We":[23],"build":[24],"on":[25,70],"our":[26,119],"previous":[27],"work":[28],"in":[29,50,114,118,137,186],"which":[30,103],"we":[31,128],"value":[34],"iteration":[35],"can":[36,139],"be":[37,140,178],"represented":[38],"by":[39],"precomposition":[40],"with":[41,105,121],"a":[42,71,75,80,170,179],"certain":[43],"optic.The":[44],"outline":[45],"main":[48],"construction":[49],"this":[51,147,162,167],"paper":[52],"is:":[53],"(1)":[54],"extend":[56],"Bellman":[58,86],"operators":[59],"optics":[62,112],"apply":[64,74],"action-value":[66],"functions":[67],"and":[68,158,173],"depend":[69],"sample.(2)":[72],"representable":[76],"contravariant":[77],"functor,":[78],"obtaining":[79],"function":[82,90],"applies":[84],"iteration.(3)":[87],"This":[88],"becomes":[91],"backward":[93],"pass":[94],"another":[96],"optic":[98],"represents":[100],"model,":[102],"interacts":[104],"an":[106,109],"environment":[107],"via":[108],"agent.Thus,":[110],"appear":[113],"two":[115],"different":[116,143],"ways":[117],"construction,":[120],"one":[122,172],"becoming":[123],"part":[124],"other.As":[127],"show,":[129],"many":[130],"classes":[134],"RL":[138,185],"seen":[141],"as":[142,163],"extremal":[144],"cases":[145],"general":[148],"setup:":[149],"dynamic":[150],"programming,":[151],"Monte":[152],"Carlo":[153],"methods,":[154],"temporal":[155],"difference":[156],"learning,":[157],"deep":[159],"RL.We":[160],"see":[161],"strong":[164],"evidence":[165],"approach":[168],"natural":[171],"believe":[174],"it":[176],"will":[177],"fruitful":[180],"way":[181],"think":[183],"about":[184],"future.":[188]},"counts_by_year":[],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-10-10T00:00:00"}