{"id":"https://openalex.org/W7140475028","doi":"https://doi.org/10.1109/lra.2026.3678143","title":"Where-to-Learn: Analytical Policy Gradient Directed Exploration for On-Policy Robotic Reinforcement Learning","display_name":"Where-to-Learn: Analytical Policy Gradient Directed Exploration for On-Policy Robotic Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7140475028","doi":"https://doi.org/10.1109/lra.2026.3678143"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3678143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678143","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.27317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130706882","display_name":"Leixin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Leixin Chang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China"],"raw_orcid":"https://orcid.org/0009-0003-8979-2162","affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130676082","display_name":"Xinchen Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xinchen Yao","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China"],"raw_orcid":"https://orcid.org/0009-0002-0501-0390","affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ben Liu","orcid":"https://orcid.org/0009-0008-6879-6259"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ben Liu","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-6879-6259","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130683693","display_name":"Liangjing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Liangjing Yang","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China"],"raw_orcid":"https://orcid.org/0000-0002-3294-0879","affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hua Chen","orcid":"https://orcid.org/0000-0002-4252-8693"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hua Chen","raw_affiliation_strings":["Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China"],"raw_orcid":"https://orcid.org/0000-0002-4252-8693","affiliations":[{"raw_affiliation_string":"Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Haining, China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5130706882"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65530502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"6","first_page":"6648","last_page":"6655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9610000252723694,"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":0.9610000252723694,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5267999768257141},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33799999952316284},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2897000014781952},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2896000146865845},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.2863999903202057},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2858000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5490000247955322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629000127315521},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.33550000190734863},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2026.3678143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678143","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2603.27317","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27317","pdf_url":"https://arxiv.org/pdf/2603.27317","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.27317","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27317","pdf_url":"https://arxiv.org/pdf/2603.27317","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140475028.pdf","grobid_xml":"https://content.openalex.org/works/W7140475028.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"On-policy":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"algorithms":[4],"have":[5],"demonstrated":[6],"great":[7],"potential":[8,56],"in":[9],"robotic":[10],"control,":[11],"where":[12],"effective":[13,93],"exploration":[14,42,66,99,129],"is":[15],"crucial":[16],"for":[17,89,142],"efficient":[18],"and":[19,91,113,122,146,151],"high-quality":[20],"policy":[21,46,70,94],"learning.":[22,95],"However,":[23],"how":[24],"to":[25,29,77,111],"encourage":[26],"the":[27,31,45,55,84,124,127,148,158],"agent":[28,85],"explore":[30],"better":[32],"trajectories":[33],"efficiently":[34],"remains":[35],"a":[36,61,73,102,138,153],"challenge.":[37],"Most":[38],"existing":[39],"methods":[40],"incentivize":[41],"by":[43],"maximizing":[44],"entropy":[47],"or":[48],"encouraging":[49],"novel":[50],"state":[51,57],"visiting":[52],"regardless":[53],"of":[54,64,126],"value.":[58],"We":[59,96,117,132],"propose":[60],"new":[62],"form":[63],"directed":[65],"that":[67],"uses":[68],"analytical":[69],"gradients":[71],"from":[72],"differentiable":[74],"dynamics":[75],"model":[76],"inject":[78],"task-aware,":[79],"physics-guided":[80],"guidance,":[81],"thereby":[82],"steering":[83],"towards":[86],"high-reward":[87],"regions":[88],"accelerated":[90],"more":[92],"integrate":[97],"our":[98,135],"approach":[100,136],"into":[101],"widely":[103],"used":[104],"on-policy":[105],"RL":[106],"algorithm,":[107],"Proximal":[108],"Policy":[109],"Optimization,":[110],"test":[112,134,150],"demonstrate":[114,123],"its":[115],"effectiveness.":[116],"conduct":[118,147],"extensive":[119],"benchmark":[120],"experiments":[121],"effectiveness":[125],"proposed":[128],"augmentation":[130],"method.":[131],"further":[133],"on":[137],"6-DOF":[139],"point-foot":[140],"robot":[141],"velocity":[143],"tracking":[144],"locomotion,":[145],"simulation":[149],"implement":[152],"successful":[154],"sim-to-real":[155],"deployment":[156],"as":[157],"ultimate":[159],"validation.":[160]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-27T00:00:00"}
