{"id":"https://openalex.org/W4401797397","doi":"https://doi.org/10.1109/aim55361.2024.10636979","title":"Open-Source Reinforcement Learning Environments Implemented in MuJoCo with Franka Manipulator","display_name":"Open-Source Reinforcement Learning Environments Implemented in MuJoCo with Franka Manipulator","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401797397","doi":"https://doi.org/10.1109/aim55361.2024.10636979"},"language":"en","primary_location":{"id":"doi:10.1109/aim55361.2024.10636979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim55361.2024.10636979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","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/A5006489811","display_name":"Zichun Xu","orcid":"https://orcid.org/0000-0002-1031-8018"},"institutions":[{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":null,"type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zichun Xu","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006702189","display_name":"Yuntao Li","orcid":"https://orcid.org/0000-0002-8039-3240"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":null,"type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuntao Li","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089233029","display_name":"Xiaohang Yang","orcid":"https://orcid.org/0000-0002-6032-4299"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":null,"type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohang Yang","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079531245","display_name":"Zhiyuan Zhao","orcid":"https://orcid.org/0000-0002-1227-5058"},"institutions":[{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":null,"type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhao","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103216579","display_name":"Lei Zhuang","orcid":"https://orcid.org/0000-0003-1113-6846"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":null,"type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhuang","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015635398","display_name":"Jingdong Zhao","orcid":"https://orcid.org/0000-0002-2074-6534"},"institutions":[{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":null,"type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Zhao","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,Heilongjiang Province,China,150001","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006489811"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"],"apc_list":null,"apc_paid":null,"fwci":1.4548,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84720478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"709","last_page":"714"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10879","display_name":"Robotic Locomotion and Control","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7997927069664001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248478889465332},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.525187611579895},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5052781701087952},{"id":"https://openalex.org/keywords/manipulator","display_name":"Manipulator (device)","score":0.42769572138786316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38652440905570984},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.25314581394195557},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21481075882911682},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15263256430625916},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14466199278831482},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.11667704582214355}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7997927069664001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248478889465332},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.525187611579895},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5052781701087952},{"id":"https://openalex.org/C2781347998","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Manipulator (device)","level":3,"score":0.42769572138786316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38652440905570984},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25314581394195557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21481075882911682},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15263256430625916},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14466199278831482},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.11667704582214355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim55361.2024.10636979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim55361.2024.10636979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1570792896","https://openalex.org/W2904246096","https://openalex.org/W2963099939","https://openalex.org/W2968116426","https://openalex.org/W3088304681","https://openalex.org/W3203417057","https://openalex.org/W3207033324","https://openalex.org/W3216772467","https://openalex.org/W4283788634","https://openalex.org/W4287113380","https://openalex.org/W4293872189","https://openalex.org/W4385430467","https://openalex.org/W4385430700","https://openalex.org/W4385626951","https://openalex.org/W6684921986","https://openalex.org/W6740801417","https://openalex.org/W6745744936","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6769035977","https://openalex.org/W6776730770","https://openalex.org/W6782766965","https://openalex.org/W6784521679","https://openalex.org/W6800004206","https://openalex.org/W6804601995","https://openalex.org/W6851774385"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"three":[3],"open-source":[4],"reinforcement":[5],"learning":[6],"environments":[7],"developed":[8],"on":[9],"the":[10,15,33,40,45,54,58,67,80,85,107,112,118],"MuJoCo":[11,21],"physics":[12],"engine":[13],"with":[14],"Franka":[16],"Emika":[17],"Panda":[18],"arm":[19],"in":[20,102],"Menagerie.":[22],"Three":[23,72],"representative":[24],"tasks,":[25,89],"push,":[26],"slide,":[27],"and":[28,48,53,62,90,98,106],"pick-and-place,":[29],"are":[30,51,76,93,100,114],"implemented":[31],"through":[32],"Gymnasium":[34],"Robotics":[35],"API,":[36],"which":[37],"inherits":[38],"from":[39],"core":[41],"of":[42,60,87],"Gymnasium.":[43],"Both":[44],"sparse":[46],"binary":[47],"dense":[49],"rewards":[50],"supported,":[52],"observation":[55],"space":[56],"contains":[57],"keys":[59],"desired":[61],"achieved":[63],"goals":[64],"to":[65,78,83,116],"follow":[66],"Multi-Goal":[68],"Reinforcement":[69],"Learning":[70],"framework.":[71],"different":[73],"off-policy":[74],"algorithms":[75],"used":[77],"validate":[79],"simulation":[81],"attributes":[82],"ensure":[84],"fidelity":[86],"all":[88,124],"benchmark":[91],"results":[92],"also":[94],"given.":[95],"Each":[96],"environment":[97,113],"task":[99],"defined":[101],"a":[103],"clean":[104],"way,":[105],"main":[108,119],"parameters":[109],"for":[110],"modifying":[111],"preserved":[115],"reflect":[117],"difference.":[120],"The":[121],"repository,":[122],"including":[123],"environments,":[125],"is":[126],"available":[127],"at":[128],"https://github.com/zichunxx/panda_mujoco_gym.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}