{"id":"https://openalex.org/W3205041129","doi":"https://doi.org/10.1109/indin45523.2021.9557406","title":"Hierarchical Reinforcement Learning for Waypoint-based Exploration in Robotic Devices","display_name":"Hierarchical Reinforcement Learning for Waypoint-based Exploration in Robotic Devices","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3205041129","doi":"https://doi.org/10.1109/indin45523.2021.9557406","mag":"3205041129"},"language":"en","primary_location":{"id":"doi:10.1109/indin45523.2021.9557406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin45523.2021.9557406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","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/A5022995247","display_name":"Jonas Zinn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]},{"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":true,"raw_author_name":"Jonas Zinn","raw_affiliation_strings":["Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]},{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210157642","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071323487","display_name":"Birgit Vogel\u2010Heuser","orcid":"https://orcid.org/0000-0003-2785-8819"},"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"]},{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Birgit Vogel-Heuser","raw_affiliation_strings":["Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]},{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210157642","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017072324","display_name":"Fabian Schuhmann","orcid":"https://orcid.org/0000-0002-3768-6494"},"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"]},{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian Schuhmann","raw_affiliation_strings":["Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]},{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210157642","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061654131","display_name":"Luis Alberto Cruz Salazar","orcid":"https://orcid.org/0000-0001-8386-5568"},"institutions":[{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]},{"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":"Luis Alberto Cruz Salazar","raw_affiliation_strings":["Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Institute of Automation and Information Systems,Munich,Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210157642"]},{"raw_affiliation_string":"Institute of Automation and Information Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210157642","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022995247"],"corresponding_institution_ids":["https://openalex.org/I4210157642","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7309107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waypoint","display_name":"Waypoint","score":0.9831046462059021},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8585042953491211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6607546806335449},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.6270825266838074},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6146851778030396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5489058494567871},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45806270837783813},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.456156849861145},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.45468616485595703},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33312028646469116},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.20193028450012207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08849534392356873}],"concepts":[{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.9831046462059021},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8585042953491211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607546806335449},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.6270825266838074},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6146851778030396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489058494567871},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45806270837783813},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.456156849861145},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.45468616485595703},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33312028646469116},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.20193028450012207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08849534392356873},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/indin45523.2021.9557406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin45523.2021.9557406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1966268398","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2575705757","https://openalex.org/W2746553466","https://openalex.org/W2749779701","https://openalex.org/W2768255130","https://openalex.org/W2786928559","https://openalex.org/W2803281228","https://openalex.org/W2904246096","https://openalex.org/W2914261249","https://openalex.org/W2921790298","https://openalex.org/W2949267040","https://openalex.org/W2949604932","https://openalex.org/W2950614095","https://openalex.org/W2951799221","https://openalex.org/W2962917939","https://openalex.org/W2963262099","https://openalex.org/W2963477884","https://openalex.org/W2963544079","https://openalex.org/W2964001908","https://openalex.org/W2964333597","https://openalex.org/W2989598077","https://openalex.org/W2991464559","https://openalex.org/W3003373508","https://openalex.org/W3029907520","https://openalex.org/W3129198075","https://openalex.org/W3136669331","https://openalex.org/W4288089349","https://openalex.org/W4300799055","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6703271639","https://openalex.org/W6734215269","https://openalex.org/W6740801417","https://openalex.org/W6748554570","https://openalex.org/W6752089545","https://openalex.org/W6757592117","https://openalex.org/W6758978475","https://openalex.org/W6759871227","https://openalex.org/W6760410039","https://openalex.org/W6770044267","https://openalex.org/W6770407973","https://openalex.org/W6773975657"],"related_works":["https://openalex.org/W2688471429","https://openalex.org/W4360939124","https://openalex.org/W2077345734","https://openalex.org/W2899287767","https://openalex.org/W2275928629","https://openalex.org/W4387126713","https://openalex.org/W2612848489","https://openalex.org/W2915444871","https://openalex.org/W2096610529","https://openalex.org/W4235170104"],"abstract_inverted_index":{"The":[0,50,69,87,107],"training":[1],"of":[2,17,22,47,95,104,109,117,129],"Deep":[3],"Reinforcement":[4,42],"Learning":[5,43],"algorithms":[6],"on":[7,114],"robotic":[8,48,105],"devices":[9],"is":[10,112],"challenging":[11],"due":[12],"to":[13,44,60,75],"their":[14],"large":[15],"number":[16,21,94],"actuators":[18],"and":[19,33,98,121],"limited":[20],"feasible":[23,96],"action":[24],"sequences.":[25],"This":[26],"paper":[27],"addresses":[28],"this":[29],"challenge":[30],"by":[31],"extending":[32],"transferring":[34],"existing":[35],"approaches":[36],"for":[37,91],"waypoint-based":[38],"exploration":[39],"with":[40],"Hierarchical":[41],"the":[45,66,76,92,110,115,127],"domain":[46,80],"devices.":[49,106],"resulting":[51],"algorithm":[52,88],"utilizes":[53],"a":[54,61,118,122],"top-level":[55,77],"policy,":[56],"which":[57],"suggests":[58],"waypoints":[59,70,97],"bottom-level":[62],"policy":[63,78],"that":[64,101],"controls":[65],"system":[67],"actuators.":[68],"can":[71],"either":[72],"be":[73,83],"provided":[74],"as":[79],"knowledge":[81],"or":[82],"learned":[84],"from":[85],"scratch.":[86],"explicitly":[89],"accounts":[90],"low":[93],"waypoint":[99],"transitions":[100],"are":[102],"characteristic":[103],"effectiveness":[108],"approach":[111],"evaluated":[113],"simulation":[116],"research":[119],"demonstrator,":[120],"separate":[123],"ablation":[124],"study":[125],"proves":[126],"importance":[128],"its":[130],"components.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
