{"id":"https://openalex.org/W3117161954","doi":"https://doi.org/10.1109/rcar49640.2020.9303280","title":"Hierarchical Reinforcement Learning Based on Continuous Subgoal Space","display_name":"Hierarchical Reinforcement Learning Based on Continuous Subgoal Space","publication_year":2020,"publication_date":"2020-09-28","ids":{"openalex":"https://openalex.org/W3117161954","doi":"https://doi.org/10.1109/rcar49640.2020.9303280","mag":"3117161954"},"language":"en","primary_location":{"id":"doi:10.1109/rcar49640.2020.9303280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar49640.2020.9303280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5100337591","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0002-5340-9737"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086740899","display_name":"Fanyu Zeng","orcid":"https://orcid.org/0000-0002-4883-5096"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanyu Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008501506","display_name":"Shuzhi Sam Ge","orcid":"https://orcid.org/0000-0001-5549-312X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Shuzhi Sam Ge","raw_affiliation_strings":["National University of Singapore, Singapore","School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049522782","display_name":"Xin Jiang","orcid":"https://orcid.org/0000-0003-3030-2694"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jiang","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100337591"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18115618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.850921630859375},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7082631587982178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7009086012840271},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6198683977127075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888143181800842},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5473898649215698},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5425245761871338},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5233579874038696},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5074688792228699},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44550788402557373},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4450414478778839},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14571928977966309}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.850921630859375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7082631587982178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009086012840271},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6198683977127075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888143181800842},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5473898649215698},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5425245761871338},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5233579874038696},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5074688792228699},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44550788402557373},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4450414478778839},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14571928977966309},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar49640.2020.9303280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar49640.2020.9303280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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":38,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1191599655","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2567015638","https://openalex.org/W2594829461","https://openalex.org/W2736601468","https://openalex.org/W2765602917","https://openalex.org/W2803281228","https://openalex.org/W2920215304","https://openalex.org/W2949267040","https://openalex.org/W2950614095","https://openalex.org/W2962887844","https://openalex.org/W2963073167","https://openalex.org/W2963161674","https://openalex.org/W2963184621","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W2963946945","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W2967853831","https://openalex.org/W4297795161","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6616173779","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6727349600","https://openalex.org/W6734215269","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6750106230","https://openalex.org/W6752089545"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W4306904969","https://openalex.org/W2144385241","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090"],"abstract_inverted_index":{"Multi-agents":[0],"are":[1,71],"designed":[2,92],"at":[3],"different":[4],"temporal":[5],"levels":[6],"to":[7,56,73,93,112,124],"decomposed":[8],"a":[9,48,86,134],"complex":[10,147],"task":[11],"into":[12],"several":[13],"simple":[14],"ones":[15],"in":[16,77,144],"hierarchical":[17,49,120],"reinforcement":[18],"learning.":[19],"At":[20],"the":[21,27,31,36,40,59,84,95,119,138],"beginning":[22],"of":[23,30,39,62,99,140],"neural":[24,69],"network":[25],"training,":[26],"great":[28],"changes":[29],"low-level":[32,79,100],"policy":[33,50,121],"would":[34],"cause":[35],"unstable":[37],"transitions":[38],"high-level":[41,81],"one.":[42],"In":[43,83],"this":[44],"paper,":[45],"we":[46],"propose":[47],"combined":[51],"with":[52,58],"PPO":[53],"and":[54,80,104,126,146],"DDPG":[55],"deal":[57],"simultaneous":[60],"training":[61],"multi-agents.":[63],"To":[64],"create":[65],"an":[66],"end-to-end":[67],"policy,":[68],"networks":[70],"employed":[72],"extract":[74],"scene":[75],"features":[76],"both":[78],"policies.":[82],"meanwhile,":[85],"novel":[87],"internal":[88],"reward":[89],"function":[90],"is":[91,110,122],"enhance":[94],"goal":[96],"achieving":[97],"ability":[98],"policy.":[101],"A":[102],"lightweight":[103],"fast":[105],"gridworld":[106],"Gym":[107],"environment,":[108],"MiniGrid,":[109],"used":[111],"test":[113],"its":[114],"validity.":[115],"We":[116],"found":[117],"that":[118],"able":[123],"explore":[125],"plan":[127],"without":[128],"dense":[129],"rewards.":[130],"This":[131],"attribute":[132],"has":[133],"considerable":[135],"influence":[136],"on":[137],"study":[139],"robot":[141],"navigation,":[142],"especially":[143],"large":[145],"environment.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}