{"id":"https://openalex.org/W2957624498","doi":"https://doi.org/10.1145/3309772.3309801","title":"Reinforcement learning using continuous states and interactive feedback","display_name":"Reinforcement learning using continuous states and interactive feedback","publication_year":2019,"publication_date":"2019-01-07","ids":{"openalex":"https://openalex.org/W2957624498","doi":"https://doi.org/10.1145/3309772.3309801","mag":"2957624498"},"language":"en","primary_location":{"id":"doi:10.1145/3309772.3309801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3309772.3309801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Applications of Intelligent Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Reinforcement_learning_using_continuous_states_and_interactive_feedback/20743420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055996958","display_name":"Angel Ayala","orcid":"https://orcid.org/0000-0003-0732-7017"},"institutions":[{"id":"https://openalex.org/I4210156023","display_name":"Universidad Central de Chile","ror":"https://ror.org/0577avk88","country_code":"CL","type":"education","lineage":["https://openalex.org/I4210156023"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Angel Ayala","raw_affiliation_strings":["Universidad Central de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Universidad Central de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I4210156023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108203587","display_name":"Claudio Henr\u00edquez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156023","display_name":"Universidad Central de Chile","ror":"https://ror.org/0577avk88","country_code":"CL","type":"education","lineage":["https://openalex.org/I4210156023"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Claudio Henr\u00edquez","raw_affiliation_strings":["Universidad Central de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Universidad Central de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I4210156023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044098673","display_name":"Francisco Cruz","orcid":"https://orcid.org/0000-0002-1131-3382"},"institutions":[{"id":"https://openalex.org/I4210156023","display_name":"Universidad Central de Chile","ror":"https://ror.org/0577avk88","country_code":"CL","type":"education","lineage":["https://openalex.org/I4210156023"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Francisco Cruz","raw_affiliation_strings":["Universidad Central de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Universidad Central de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I4210156023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055996958"],"corresponding_institution_ids":["https://openalex.org/I4210156023"],"apc_list":null,"apc_paid":null,"fwci":1.5874,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87735849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9797999858856201,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9645000100135803,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9122413396835327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7538720965385437},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6308572888374329},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.5962019562721252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5148569941520691},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5132379531860352},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49060335755348206},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4419345259666443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3379497528076172},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10850861668586731},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08815750479698181},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0818416178226471},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0663997232913971}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9122413396835327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538720965385437},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6308572888374329},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.5962019562721252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5148569941520691},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5132379531860352},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49060335755348206},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4419345259666443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3379497528076172},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10850861668586731},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08815750479698181},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0818416178226471},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0663997232913971},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3309772.3309801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3309772.3309801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Applications of Intelligent Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30129401","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401102","display_name":"Own your potential (DEAKIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/20743420","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Reinforcement_learning_using_continuous_states_and_interactive_feedback/20743420","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20743420","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Reinforcement_learning_using_continuous_states_and_interactive_feedback/20743420","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323458","display_name":"Universidad de Chile","ror":"https://ror.org/047gc3g35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W46130386","https://openalex.org/W1515851193","https://openalex.org/W2020954172","https://openalex.org/W2792217087","https://openalex.org/W3037207827","https://openalex.org/W4230853744"],"related_works":["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","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2068306051"],"abstract_inverted_index":{"Research":[0],"in":[1,84,88,106,122],"intelligent":[2],"systems":[3],"field":[4],"has":[5],"led":[6],"to":[7,13,28,31,90,124],"different":[8,82],"learning":[9,19,43,113,129],"methods":[10],"for":[11,51],"machines":[12],"acquire":[14],"knowledge,":[15],"among":[16],"them,":[17],"reinforcement":[18,42,128],"(RL).":[20],"Given":[21],"the":[22,25,40,52,61,68,85,92,107],"problem":[23,62],"of":[24,49,54,63,94,101],"time":[26],"required":[27],"learn":[29],"how":[30],"develop":[32],"a":[33,47,98,111],"problem,":[34],"using":[35,81,116],"RL":[36],"this":[37,57,72,95],"work":[38,58],"tackles":[39],"interactive":[41,69,120],"(IRL)":[44],"approach":[45,96],"as":[46],"way":[48],"solution":[50],"training":[53],"agents.":[55],"Furthermore,":[56],"also":[59],"addresses":[60],"continuous":[64,117],"representations":[65,83],"along":[66],"with":[67,78],"approach.":[70],"In":[71],"regards,":[73],"we":[74],"have":[75],"performed":[76],"experiments":[77],"simulated":[79,108],"environments":[80,109],"state":[86],"vector":[87],"order":[89],"show":[91,110],"efficiency":[93],"under":[97],"certain":[99],"probability":[100],"interaction.":[102],"The":[103],"obtained":[104],"results":[105],"faster":[112],"convergence":[114],"when":[115],"states":[118],"and":[119,126],"feedback":[121],"comparison":[123],"discrete":[125],"autonomous":[127],"respectively.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}