{"id":"https://openalex.org/W4389667013","doi":"https://doi.org/10.1109/iros55552.2023.10341769","title":"Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions","display_name":"Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667013","doi":"https://doi.org/10.1109/iros55552.2023.10341769"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341769","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073985865","display_name":"Xiangtong Yao","orcid":"https://orcid.org/0000-0003-2556-3072"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiangtong Yao","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Germany","School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060444894","display_name":"Zhenshan Bing","orcid":"https://orcid.org/0000-0002-0896-2517"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhenshan Bing","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Germany","School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072201303","display_name":"Genghang Zhuang","orcid":"https://orcid.org/0000-0003-2478-7912"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Genghang Zhuang","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Germany","School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016558517","display_name":"Kejia Chen","orcid":"https://orcid.org/0000-0001-7700-290X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kejia Chen","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Germany","School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103182284","display_name":"Hongkuan Zhou","orcid":"https://orcid.org/0000-0002-1329-2626"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hongkuan Zhou","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Germany","School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768452","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0003-0359-7810"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,China","Pazhou Lab, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Pazhou Lab, Guangzhou, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Germany","School of Computation, Information and Technology, Technical University of Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5574","last_page":"5581"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996999979019165,"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":0.9966999888420105,"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/generalization","display_name":"Generalization","score":0.8758316040039062},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8415141701698303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8153982162475586},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6754178404808044},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6043198108673096},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5925567746162415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5664907097816467},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4888167083263397},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39599883556365967},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10368132591247559},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0645965039730072}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8758316040039062},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8415141701698303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153982162475586},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6754178404808044},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6043198108673096},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5925567746162415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5664907097816467},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4888167083263397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39599883556365967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10368132591247559},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0645965039730072},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341769","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2035094553","https://openalex.org/W2081580037","https://openalex.org/W2150663697","https://openalex.org/W2158782408","https://openalex.org/W2962690139","https://openalex.org/W3035454705","https://openalex.org/W3039459278","https://openalex.org/W3098082936","https://openalex.org/W3175584021","https://openalex.org/W3199421945","https://openalex.org/W4250316425","https://openalex.org/W4283365039","https://openalex.org/W4285294350","https://openalex.org/W4287749615","https://openalex.org/W4382318723","https://openalex.org/W4383097530","https://openalex.org/W4402673453","https://openalex.org/W6636142636","https://openalex.org/W6736057607","https://openalex.org/W6756254808","https://openalex.org/W6760698134","https://openalex.org/W6769596995","https://openalex.org/W6771437833","https://openalex.org/W6779868169","https://openalex.org/W6801810553","https://openalex.org/W6802366246"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2501594388","https://openalex.org/W3130669838","https://openalex.org/W2785397462","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W4283332751","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Meta-reinforcement":[0],"learning":[1,63,82,89,93,125],"(meta-RL)":[2],"is":[3],"a":[4,86],"promising":[5],"approach":[6],"that":[7,91,116],"enables":[8,92],"the":[9,28,39,47,78,122],"agent":[10],"to":[11,27],"learn":[12],"new":[13,65,94],"tasks":[14,95],"quickly.":[15],"However,":[16],"most":[17],"meta-RL":[18,37,74],"algorithms":[19],"show":[20,115],"poor":[21],"generalization":[22,40,80,123],"in":[23,107],"multi-task":[24],"scenarios":[25],"due":[26],"insufficient":[29],"task":[30],"information":[31],"provided":[32],"only":[33],"by":[34,42],"rewards.":[35],"Language-conditioned":[36],"improves":[38],"capability":[41],"matching":[43],"language":[44,54,71,101],"instructions":[45,55,72],"with":[46,97],"agent's":[48],"behaviors.":[49],"While":[50],"both":[51],"behaviors":[52],"and":[53,70,81,100,112,124],"have":[56],"symmetry,":[57],"which":[58],"can":[59,75,119],"speed":[60],"up":[61],"human":[62],"of":[64,127],"knowledge.":[66],"Thus,":[67],"combining":[68],"symmetry":[69],"into":[73],"help":[76],"improve":[77,121],"algorithm's":[79],"efficiency.":[83],"We":[84,103],"propose":[85],"dual-MDP":[87],"meta-reinforcement":[88,128],"method":[90,106,118],"efficiently":[96],"symmetrical":[98],"behav-iors":[99],"instructions.":[102],"evaluate":[104],"our":[105,117],"mul-tiple":[108],"challenging":[109],"manipulation":[110],"tasks,":[111],"experimental":[113],"results":[114],"greatly":[120],"efficiency":[126],"learning.":[129],"Videos":[130],"are":[131],"available":[132],"at":[133],"https://tumi6robot.wixsite.com/symmetry/.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}