{"id":"https://openalex.org/W7133326622","doi":"https://doi.org/10.48550/arxiv.2603.02104","title":"ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation","display_name":"ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133326622","doi":"https://doi.org/10.48550/arxiv.2603.02104"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006963102","display_name":"Xuerui Wang","orcid":"https://orcid.org/0000-0001-6330-419X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Xuerui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058986919","display_name":"Guangyu Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Guangyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127987838","display_name":"Tianhong Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Tianhong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128005919","display_name":"Bintao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Bintao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061104235","display_name":"Shuangyao Huang","orcid":"https://orcid.org/0000-0002-7649-8496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shuangyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009338657","display_name":"Wenzhang Zhang","orcid":"https://orcid.org/0000-0001-9549-5832"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenzhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001822062","display_name":"Hengyan Liu","orcid":"https://orcid.org/0000-0003-1237-8177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hengyan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006963102"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8008000254631042,"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":0.8008000254631042,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.14180000126361847,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.01119999960064888,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7741000056266785},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.6625999808311462},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6554999947547913},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5767999887466431},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5547999739646912},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4535999894142151}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7741000056266785},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381999850273132},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545799970626831},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3127000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02104","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Goal-conditioned":[0],"reinforcement":[1],"learning":[2,32,39,61,74],"has":[3],"shown":[4],"considerable":[5],"potential":[6],"in":[7,23,133],"robotic":[8,122],"manipulation;":[9],"however,":[10],"existing":[11],"approaches":[12],"remain":[13],"limited":[14],"by":[15,30,76],"their":[16],"reliance":[17],"on":[18,85,120],"prioritizing":[19],"collected":[20],"experience,":[21],"resulting":[22],"suboptimal":[24],"performance":[25],"across":[26],"diverse":[27],"tasks.":[28],"Inspired":[29],"human":[31],"behaviors,":[33],"we":[34],"propose":[35],"a":[36,59],"more":[37],"comprehensive":[38],"paradigm,":[40],"ACDC,":[41],"which":[42],"integrates":[43],"multidimensional":[44],"Adaptive":[45],"Curriculum":[46],"(AC)":[47],"Planning":[48],"with":[49,113],"Dynamic":[50],"Contrastive":[51],"(DC)":[52],"Control":[53],"to":[54],"guide":[55],"the":[56,66,69,73,86,94,97,101,114,130],"agent":[57],"along":[58],"well-designed":[60],"trajectory.":[62],"More":[63],"specifically,":[64],"at":[65],"planning":[67],"level,":[68,96],"AC":[70],"component":[71,99],"schedules":[72],"curriculum":[75,102,116],"dynamically":[77],"balancing":[78],"diversity-driven":[79],"exploration":[80],"and":[81,90,137],"quality-driven":[82],"exploitation":[83],"based":[84],"agent's":[87],"success":[88,140],"rate":[89],"training":[91],"progress.":[92],"At":[93],"control":[95],"DC":[98],"implements":[100],"plan":[103],"through":[104],"norm-constrained":[105],"contrastive":[106],"learning,":[107],"enabling":[108],"magnitude-guided":[109],"experience":[110],"selection":[111],"aligned":[112],"current":[115],"focus.":[117],"Extensive":[118],"experiments":[119],"challenging":[121],"manipulation":[123],"tasks":[124],"demonstrate":[125],"that":[126],"ACDC":[127],"consistently":[128],"outperforms":[129],"state-of-the-art":[131],"baselines":[132],"both":[134],"sample":[135],"efficiency":[136],"final":[138],"task":[139],"rate.":[141]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}