{"id":"https://openalex.org/W4413945021","doi":"https://doi.org/10.1109/icra55743.2025.11128552","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","display_name":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945021","doi":"https://doi.org/10.1109/icra55743.2025.11128552"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128552","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/A5101716360","display_name":"Dohyeong Kim","orcid":"https://orcid.org/0000-0002-3141-413X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dohyeong Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071500991","display_name":"Hyeok\u2010jin Kwon","orcid":"https://orcid.org/0000-0002-6106-0619"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeokjin Kwon","raw_affiliation_strings":["Interdisciplinary Program in Artificial Intelligence and ASRI, Seoul National University,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence and ASRI, Seoul National University,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100698865","display_name":"Junseok Kim","orcid":"https://orcid.org/0000-0002-0484-9189"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junseok Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024425360","display_name":"Gunmin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunmin Lee","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033764106","display_name":"Songhwai Oh","orcid":"https://orcid.org/0000-0002-9781-2018"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Songhwai Oh","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101716360"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":11.4397,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98193012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10268","last_page":"10274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.97079998254776,"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":0.97079998254776,"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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9498999714851379,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular 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":0.891751766204834},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6865563988685608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6606747508049011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5472762584686279},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4371694028377533},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33012884855270386},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12473812699317932},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.052030593156814575}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.891751766204834},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6865563988685608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6606747508049011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472762584686279},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4371694028377533},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33012884855270386},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12473812699317932},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.052030593156814575}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128552","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":15,"referenced_works":["https://openalex.org/W2060846151","https://openalex.org/W2796290181","https://openalex.org/W3093922502","https://openalex.org/W3175254947","https://openalex.org/W3176539729","https://openalex.org/W3207033168","https://openalex.org/W4206497039","https://openalex.org/W4226143977","https://openalex.org/W4229044820","https://openalex.org/W4285600796","https://openalex.org/W4287266177","https://openalex.org/W4385430644","https://openalex.org/W4396910086","https://openalex.org/W4401415792","https://openalex.org/W4402354000"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"As":[0],"the":[1,11,29,68,101],"complexity":[2],"of":[3,13,37,43,113],"tasks":[4,61,115,130],"addressed":[5],"through":[6,32],"reinforcement":[7],"learning":[8],"(RL)":[9],"increases,":[10],"definition":[12],"reward":[14,40,49],"functions":[15,52],"also":[16],"has":[17,106,124],"become":[18],"highly":[19],"complicated.":[20],"We":[21],"introduce":[22,84],"an":[23],"RL":[24,57,134,137],"method":[25,105],"aimed":[26],"at":[27,143],"simplifying":[28],"reward-shaping":[30],"process":[31],"intuitive":[33],"strategies.":[34],"Initially,":[35],"instead":[36],"a":[38,54,85,111],"single":[39],"function":[41],"composed":[42],"various":[44],"terms,":[45],"we":[46,66,83],"define":[47,74],"multiple":[48,75],"and":[50,73,77,119,135],"cost":[51],"within":[53],"constrained":[55,136],"multi-objective":[56],"(CMORL)":[58],"framework.":[59],"For":[60],"involving":[62],"sequential":[63],"complex":[64],"movements,":[65],"segment":[67],"task":[69],"into":[70],"distinct":[71],"stages":[72],"rewards":[76,95],"costs":[78],"for":[79],"each":[80],"stage.":[81],"Finally,":[82],"practical":[86],"CMORL":[87],"algorithm":[88],"that":[89],"maximizes":[90],"objectives":[91],"based":[92],"on":[93],"these":[94],"while":[96],"satisfying":[97],"constraints":[98],"defined":[99],"by":[100],"costs.":[102],"The":[103],"proposed":[104],"been":[107,125],"successfully":[108,128],"demonstrated":[109],"across":[110],"variety":[112],"acrobatic":[114],"in":[116],"both":[117],"simulation":[118],"real-world":[120],"environments.":[121],"Additionally,":[122],"it":[123],"shown":[126],"to":[127,132],"perform":[129],"compared":[131],"existing":[133],"algorithms.":[138],"Our":[139],"code":[140],"is":[141],"available":[142],"https://github.com/rllab-snu/Stage-Wise-CMORL.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}