{"id":"https://openalex.org/W7135200683","doi":"https://doi.org/10.1109/lra.2026.3673900","title":"Climb With SHERPA: Heuristic-Guided Reinforcement Learning via Segmented Experience Relay","display_name":"Climb With SHERPA: Heuristic-Guided Reinforcement Learning via Segmented Experience Relay","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135200683","doi":"https://doi.org/10.1109/lra.2026.3673900"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3673900","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3673900","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2026.3673900","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Minji Kim","orcid":"https://orcid.org/0009-0001-0615-4305"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minji Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-0615-4305","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129009937","display_name":"Ganghun 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":"Ganghun Lee","raw_affiliation_strings":["Interdisciplinary Program in Artificial Intelligence and AIIS, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-5575-6441","affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence and AIIS, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124900179","display_name":"Minsu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I165677929","display_name":"Sungshin Women's University","ror":"https://ror.org/0500xzf72","country_code":"KR","type":"education","lineage":["https://openalex.org/I165677929"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Lee","raw_affiliation_strings":["School of AI Convergence, Sungshin Women’s University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9601-3863","affiliations":[{"raw_affiliation_string":"School of AI Convergence, Sungshin Women’s University, Seoul, South Korea","institution_ids":["https://openalex.org/I165677929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129032510","display_name":"Byoung-Tak Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byoung-Tak Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-9890-0389","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"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":0.53340803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"5","first_page":"5883","last_page":"5890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.450300008058548,"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":0.450300008058548,"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/T10803","display_name":"Innovative Human-Technology Interaction","score":0.05550000071525574,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.4867999851703644},{"id":"https://openalex.org/keywords/relay","display_name":"Relay","score":0.4659999907016754},{"id":"https://openalex.org/keywords/climb","display_name":"Climb","score":0.3903999924659729},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3199000060558319},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3181000053882599},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2718999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5688999891281128},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C2778156585","wikidata":"https://www.wikidata.org/wiki/Q174053","display_name":"Relay","level":3,"score":0.4659999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124000072479248},{"id":"https://openalex.org/C2778168010","wikidata":"https://www.wikidata.org/wiki/Q1499786","display_name":"Climb","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.35910001397132874},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3673900","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3673900","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2026.3673900","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2026.3673900","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2025676199","display_name":null,"funder_award_id":"RS-2022-I1220951-LBA/10%","funder_id":"https://openalex.org/F4320334874","funder_display_name":"Defense Acquisition Program Administration"},{"id":"https://openalex.org/G3092983305","display_name":null,"funder_award_id":"RS-2025-25453780/10%","funder_id":"https://openalex.org/F4320334879","funder_display_name":"Korea Evaluation Institute of Industrial Technology"},{"id":"https://openalex.org/G3490496830","display_name":null,"funder_award_id":"KRIT-CT-23-003/20%","funder_id":"https://openalex.org/F4320334874","funder_display_name":"Defense Acquisition Program Administration"},{"id":"https://openalex.org/G6958392815","display_name":null,"funder_award_id":"RS-2025-25460896/10%","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"}],"funders":[{"id":"https://openalex.org/F2292562827","display_name":"Korea Research Institute for Defense Technology Planning and Advancement","ror":null},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"},{"id":"https://openalex.org/F4320334879","display_name":"Korea Evaluation Institute of Industrial Technology","ror":"https://ror.org/03z9cwa38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"sparse-reward,":[1],"long-horizon":[2,114],"domains,":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"often":[7],"suffers":[8],"from":[9,84,95],"slow":[10],"convergence":[11],"and":[12,25,55,65,85,109,121,124],"instability,":[13],"complicating":[14],"robotic":[15],"manipulation.":[16],"Previous":[17],"heuristic-guided":[18,122],"approaches":[19],"have":[20],"relied":[21],"on":[22,133],"step-level":[23],"actions":[24],"imitation":[26],"loss,":[27],"but":[28],"struggle":[29],"to":[30,82,98],"maintain":[31],"temporal":[32],"coherence":[33],"or":[34],"solve":[35],"multi-stage":[36],"tasks.":[37],"We":[38,89],"present":[39],"SHERPA":[40,73,116],"(Segmented":[41],"Heuristic":[42],"Experience":[43],"Relay":[44],"for":[45],"Policy":[46],"Assistance),":[47],"which":[48],"alternates":[49],"control":[50],"between":[51],"a":[52,134],"heuristic":[53,87,96],"policy":[54,58,81],"an":[56],"RL":[57,77],"in":[59,106],"contiguous":[60],"segments,":[61],"preserving":[62],"coherent":[63],"sub-trajectories":[64],"yielding":[66],"more":[67],"stable":[68],"learning.":[69],"Unlike":[70],"imitation-based":[71],"designs,":[72],"learns":[74],"entirely":[75],"through":[76],"optimization,":[78],"enabling":[79],"the":[80,107],"benefit":[83],"surpass":[86],"guidance.":[88],"also":[90],"incorporate":[91],"phase-specific":[92],"rewards":[93],"derived":[94],"rules":[97],"provide":[99],"targeted":[100],"subgoal":[101],"feedback.":[102],"Across":[103],"ten":[104],"tasks":[105],"Fetch":[108],"Panda":[110],"suites,":[111],"including":[112],"four":[113],"benchmarks,":[115],"consistently":[117],"outperforms":[118],"RL,":[119],"IL,":[120],"baselines":[123],"demonstrates":[125],"robustness":[126],"even":[127],"under":[128],"degraded":[129],"heuristics.":[130],"Real-world":[131],"experiments":[132],"UR5":[135],"robot":[136],"further":[137],"confirm":[138],"SHERPA's":[139],"practical":[140],"scalability.":[141]},"counts_by_year":[],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2026-03-14T00:00:00"}