{"id":"https://openalex.org/W4323240727","doi":"https://doi.org/10.5220/0011633400003393","title":"Data Augmentation Through Expert-Guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning","display_name":"Data Augmentation Through Expert-Guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323240727","doi":"https://doi.org/10.5220/0011633400003393"},"language":"en","primary_location":{"id":"doi:10.5220/0011633400003393","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011633400003393","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 15th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.5220/0011633400003393","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043519978","display_name":"Giorgio Angelotti","orcid":"https://orcid.org/0000-0002-1878-5833"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I193033237","display_name":"Institut Sup\u00e9rieur de l'A\u00e9ronautique et de l'Espace (ISAE-SUPAERO)","ror":"https://ror.org/04gyj6s21","country_code":"FR","type":"education","lineage":["https://openalex.org/I193033237"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giorgio Angelotti","raw_affiliation_strings":["ANITI, University of Toulouse, France, --- Select a Country ---","ISAE-SUPAERO, University of Toulouse, France, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANITI, University of Toulouse, France, --- Select a Country ---","institution_ids":["https://openalex.org/I17866349"]},{"raw_affiliation_string":"ISAE-SUPAERO, University of Toulouse, France, --- Select a Country ---","institution_ids":["https://openalex.org/I193033237"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001788642","display_name":"Nicolas Drougard","orcid":"https://orcid.org/0000-0003-0002-9973"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I193033237","display_name":"Institut Sup\u00e9rieur de l'A\u00e9ronautique et de l'Espace (ISAE-SUPAERO)","ror":"https://ror.org/04gyj6s21","country_code":"FR","type":"education","lineage":["https://openalex.org/I193033237"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Drougard","raw_affiliation_strings":["ANITI, University of Toulouse, France, --- Select a Country ---","ISAE-SUPAERO, University of Toulouse, France, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANITI, University of Toulouse, France, --- Select a Country ---","institution_ids":["https://openalex.org/I17866349"]},{"raw_affiliation_string":"ISAE-SUPAERO, University of Toulouse, France, --- Select a Country ---","institution_ids":["https://openalex.org/I193033237"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019098556","display_name":"Caroline Ponzoni Carvalho Chanel","orcid":"https://orcid.org/0000-0003-3578-4186"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I193033237","display_name":"Institut Sup\u00e9rieur de l'A\u00e9ronautique et de l'Espace (ISAE-SUPAERO)","ror":"https://ror.org/04gyj6s21","country_code":"FR","type":"education","lineage":["https://openalex.org/I193033237"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Caroline Chanel","raw_affiliation_strings":["ANITI, University of Toulouse, France, --- Select a Country ---","ISAE-SUPAERO, University of Toulouse, France, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANITI, University of Toulouse, France, --- Select a Country ---","institution_ids":["https://openalex.org/I17866349"]},{"raw_affiliation_string":"ISAE-SUPAERO, University of Toulouse, France, --- Select a Country ---","institution_ids":["https://openalex.org/I193033237"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37958522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9771000146865845,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9771000146865845,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9639000296592712,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9563000202178955,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081915378570557},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7936334609985352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6620314717292786},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6569806933403015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6157654523849487},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.596956193447113},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5009362697601318},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46479979157447815},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46278125047683716},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45987385511398315},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4144183099269867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081915378570557},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7936334609985352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6620314717292786},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6569806933403015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6157654523849487},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.596956193447113},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5009362697601318},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46479979157447815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46278125047683716},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45987385511398315},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4144183099269867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0011633400003393","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011633400003393","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 15th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0011633400003393","is_oa":true,"landing_page_url":"http://dx.doi.org/10.5220/0011633400003393","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 15th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1533853869","https://openalex.org/W1583912456","https://openalex.org/W1688218840","https://openalex.org/W1997303620","https://openalex.org/W2014041755","https://openalex.org/W2145339207","https://openalex.org/W2397240726","https://openalex.org/W2936774411","https://openalex.org/W2954996726","https://openalex.org/W2963641970","https://openalex.org/W2992005611","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3216574209","https://openalex.org/W4221146510","https://openalex.org/W4287642891","https://openalex.org/W4287714048","https://openalex.org/W4287749615","https://openalex.org/W4287863878","https://openalex.org/W4293849739","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"Offline":[0,121],"estimation":[1],"of":[2,6,30,40],"the":[3,20,24,28,31,41,84,94,98,101,133,160,170,176,180],"dynamical":[4],"model":[5,32],"a":[7,13,91,112,145,165],"Markov":[8],"Decision":[9],"Process":[10],"(MDP)":[11],"is":[12,33],"non-trivial":[14],"task":[15],"that":[16,49,159],"greatly":[17],"depends":[18],"on":[19,54,152],"data":[21,86,105],"available":[22],"in":[23,69,93,140,148,179],"learning":[25],"phase.":[26],"Sometimes":[27],"dynamics":[29],"invariant":[34],"with":[35],"respect":[36],"to":[37,82,90,115,135,164],"some":[38],"transformations":[39],"current":[42],"state":[43],"and":[44,74,100,155,173],"action.":[45],"Recent":[46],"works":[47],"showed":[48],"an":[50,120],"expert-guided":[51],"pipeline":[52],"relying":[53],"Density":[55],"Estimation":[56],"methods":[57],"as":[58,111],"Deep":[59],"Neural":[60],"Network":[61],"based":[62,151],"Normalizing":[63],"Flows":[64],"effectively":[65],"detects":[66],"this":[67,129],"structure":[68],"deterministic":[70],"environments,":[71],"both":[72],"categorical":[73,149],"continuous-valued.":[75],"The":[76],"acquired":[77],"knowledge":[78],"can":[79,108],"be":[80,109,116],"exploited":[81,110],"augment":[83],"original":[85],"set,":[87],"leading":[88],"eventually":[89],"reduction":[92],"distributional":[95],"shift":[96],"between":[97],"true":[99],"learned":[102,171],"model.":[103],"Such":[104],"augmentation":[106],"technique":[107],"preliminary":[113],"process":[114],"executed":[117],"before":[118],"adopting":[119],"Reinforcement":[122],"Learning":[123],"architecture,":[124],"increasing":[125],"its":[126],"performance.":[127],"In":[128],"work":[130],"we":[131,143,157],"extend":[132],"paradigm":[134],"also":[136],"tackle":[137],"non-deterministic":[138],"MDPs,":[139],"particular,":[141],"1)":[142],"propose":[144],"detection":[146],"threshold":[147],"environments":[150],"statistical":[153],"distances,":[154],"2)":[156],"show":[158],"former":[161],"results":[162],"lead":[163],"performance":[166],"improvement":[167],"when":[168],"solving":[169],"MDP":[172],"then":[174],"applying":[175],"optimized":[177],"policy":[178],"real":[181],"environment.":[182]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}