{"id":"https://openalex.org/W4413917690","doi":"https://doi.org/10.1109/icra55743.2025.11128043","title":"Simplifying Reward Design in Complex Robotics: Average-Reward Maximum Entropy Reinforcement Learning","display_name":"Simplifying Reward Design in Complex Robotics: Average-Reward Maximum Entropy Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917690","doi":"https://doi.org/10.1109/icra55743.2025.11128043"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025797799","display_name":"Jean Seong Bjorn Choe","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jean Seong Bjorn Choe","raw_affiliation_strings":["School of Electrical Engineering, Korea University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010233239","display_name":"Bumkyu Choi","orcid":"https://orcid.org/0000-0002-5327-4502"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bumkyu Choi","raw_affiliation_strings":["School of Electrical Engineering, Korea University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068766413","display_name":"Jong-kook Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-kook Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28381655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11729","display_name":"Product Development and Customization","score":0.8274000287055969,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11729","display_name":"Product Development and Customization","score":0.8274000287055969,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8256999850273132,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.7741000056266785,"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":0.791080117225647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7016497850418091},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6412448883056641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5766725540161133},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5205844044685364},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4911176860332489},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4458777606487274},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2903960943222046}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.791080117225647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7016497850418091},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6412448883056641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5766725540161133},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5205844044685364},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4911176860332489},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4458777606487274},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2903960943222046},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2847132741","https://openalex.org/W2904246096","https://openalex.org/W3108634522","https://openalex.org/W3122949669","https://openalex.org/W3126321819","https://openalex.org/W3152878473","https://openalex.org/W3192314531","https://openalex.org/W4225014288","https://openalex.org/W4390357269","https://openalex.org/W4401025088"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"This":[0,126],"paper":[1],"presents":[2],"a":[3,35,64],"novel":[4],"approach":[5,89],"to":[6],"addressing":[7],"the":[8,16,22,28,43,46,50,61,71,75,81,84,129,132],"control":[9,99,124,137],"challenges":[10],"of":[11,45,63,83,131],"underactuated":[12],"systems,":[13],"focusing":[14],"on":[15,21,107,114,121],"swing-up":[17],"and":[18,49,97],"stabilisation":[19],"tasks":[20],"double":[23,109],"pendulum":[24,110],"system.":[25],"We":[26,86],"propose":[27],"Average-Reward":[29],"Entropy":[30],"Advantage":[31],"Policy":[32],"Optimisation":[33],"(AR-EAPO),":[34],"model-free":[36],"reinforcement":[37],"learning":[38],"(RL)":[39],"algorithm":[40],"that":[41],"integrates":[42],"strengths":[44],"average-reward":[47,133],"RL":[48,53,79,95],"maximum":[51],"entropy":[52],"(MaxEnt":[54],"RL).":[55],"The":[56],"average":[57],"reward":[58,66],"criterion":[59,134],"allows":[60],"use":[62],"simple":[65],"function":[67],"by":[68],"naturally":[69],"promoting":[70],"longterm":[72],"goals,":[73],"at":[74],"same":[76],"time":[77],"MaxEnt":[78],"encourages":[80],"robustness":[82],"policy.":[85],"validate":[87],"our":[88],"through":[90],"simulations,":[91],"consistently":[92],"outperforming":[93],"standard":[94],"baselines":[96],"traditional":[98],"methods.":[100],"Also,":[101],"we":[102],"provide":[103],"preliminary":[104],"test":[105],"results":[106],"real":[108],"hardware.":[111],"Additional":[112],"experiments":[113],"MuJoCo":[115],"environments":[116],"further":[117],"demonstrate":[118],"AR-EAPO's":[119],"efficacy":[120],"general":[122],"continuous":[123],"tasks.":[125],"work":[127],"underscores":[128],"potential":[130],"in":[135],"simplifying":[136],"design":[138],"while":[139],"achieving":[140],"superior":[141],"results.":[142]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}