{"id":"https://openalex.org/W4408061819","doi":"https://doi.org/10.5220/0013247300003890","title":"Environment Descriptions for Usability and Generalisation in Reinforcement Learning","display_name":"Environment Descriptions for Usability and Generalisation in Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408061819","doi":"https://doi.org/10.5220/0013247300003890"},"language":"en","primary_location":{"id":"doi:10.5220/0013247300003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013247300003890","pdf_url":null,"source":null,"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":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013247300003890","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049574317","display_name":"Dennis J. N. J. Soemers","orcid":"https://orcid.org/0000-0003-3241-8957"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dennis Soemers","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033216620","display_name":"Spyridon Samothrakis","orcid":"https://orcid.org/0000-0003-1902-9690"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Spyridon Samothrakis","raw_affiliation_strings":["Institute for Analytics and Data Science, University of Essex, Colchester, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Analytics and Data Science, University of Essex, Colchester, U.K","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002817190","display_name":"Kurt Driessens","orcid":"https://orcid.org/0000-0001-7871-2495"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kurt Driessens","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013661099","display_name":"Mark H. M. Winands","orcid":"https://orcid.org/0000-0002-0125-0824"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mark Winands","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03048962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"983","last_page":"992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10672","display_name":"Design Education and Practice","score":0.3752000033855438,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10672","display_name":"Design Education and Practice","score":0.3752000033855438,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/usability","display_name":"Usability","score":0.8893023133277893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519057989120483},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7407851219177246},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5919414162635803},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47452178597450256},{"id":"https://openalex.org/keywords/usability-engineering","display_name":"Usability engineering","score":0.43442100286483765},{"id":"https://openalex.org/keywords/pluralistic-walkthrough","display_name":"Pluralistic walkthrough","score":0.4324764907360077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34755396842956543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10895848274230957}],"concepts":[{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.8893023133277893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519057989120483},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7407851219177246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5919414162635803},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47452178597450256},{"id":"https://openalex.org/C100302975","wikidata":"https://www.wikidata.org/wiki/Q1642623","display_name":"Usability engineering","level":3,"score":0.43442100286483765},{"id":"https://openalex.org/C188688815","wikidata":"https://www.wikidata.org/wiki/Q7205541","display_name":"Pluralistic walkthrough","level":3,"score":0.4324764907360077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34755396842956543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10895848274230957},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013247300003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013247300003890","pdf_url":null,"source":null,"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":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:openaire/9a213eaf-6e8d-4b38-b180-44c24a3ef560","is_oa":false,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/9a213eaf-6e8d-4b38-b180-44c24a3ef560","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Soemers, D J N J, Samothrakis, S, Driessens, K & Winands, M H M 2025, Environment Descriptions for Usability and Generalisation in Reinforcement Learning. in Proceedings of the 17th International Conference on Agents and Artificial Intelligence. vol. 3, pp. 983-992. https://doi.org/10.5220/0013247300003890","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.5220/0013247300003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013247300003890","pdf_url":null,"source":null,"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":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2071861739","https://openalex.org/W2171288728","https://openalex.org/W2622976019","https://openalex.org/W4253383846","https://openalex.org/W2004547170","https://openalex.org/W2024422252","https://openalex.org/W4386999422","https://openalex.org/W2347087521","https://openalex.org/W1727576116","https://openalex.org/W2167788256"],"abstract_inverted_index":{"The":[0],"majority":[1],"of":[2,37,42,65,94,109,120,130],"current":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"research":[7,72],"involves":[8],"training":[9],"and":[10,24,105],"deploying":[11],"agents":[12,111],"in":[13,20,83,127],"environments":[14,80,116,122],"that":[15,123],"are":[16,81],"implemented":[17],"by":[18],"engineers":[19],"general-purpose":[21],"programming":[22],"languages":[23],"more":[25,62],"advanced":[26],"frameworks":[27],"such":[28,96],"as":[29],"CUDA":[30],"or":[31,48,86],"JAX.":[32],"This":[33,55],"makes":[34],"the":[35,71,92,107,118],"application":[36],"RL":[38],"to":[39,45,60,74,112,114],"novel":[40],"problems":[41],"interest":[43],"inaccessible":[44],"small":[46],"organisations":[47],"private":[49],"individuals":[50],"with":[51],"insufficient":[52],"engineering":[53],"expertise.":[54],"position":[56],"paper":[57],"argues":[58],"that,":[59],"enable":[61],"widespread":[63],"adoption":[64],"RL,":[66,95],"it":[67],"is":[68],"important":[69],"for":[70],"community":[73],"shift":[75],"focus":[76],"towards":[77],"methodologies":[78],"where":[79],"described":[82,126],"user-friendly":[84],"domain-specific":[85],"natural":[87],"languages.":[88],"Aside":[89],"from":[90],"improving":[91],"usability":[93],"language-based":[97],"environment":[98],"descriptions":[99],"may":[100],"also":[101],"provide":[102],"valuable":[103],"context":[104],"boost":[106],"ability":[108],"trained":[110],"generalise":[113],"unseen":[115],"within":[117],"set":[119],"all":[121],"can":[124],"be":[125],"any":[128],"language":[129],"choice.":[131]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}