{"id":"https://openalex.org/W4390482484","doi":"https://doi.org/10.1109/cis-ram55796.2023.10370762","title":"Evaluating Optimization Approaches for Deep-Reinforcement-Learning-based Navigation Agents","display_name":"Evaluating Optimization Approaches for Deep-Reinforcement-Learning-based Navigation Agents","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4390482484","doi":"https://doi.org/10.1109/cis-ram55796.2023.10370762"},"language":"en","primary_location":{"id":"doi:10.1109/cis-ram55796.2023.10370762","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cis-ram55796.2023.10370762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM)","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/A5044968499","display_name":"Linh K\u00e4stner","orcid":"https://orcid.org/0000-0001-5263-4687"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]},{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Linh K\u00e4stner","raw_affiliation_strings":["Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]},{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104222875","display_name":"Liam Roberts","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]},{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Liam Roberts","raw_affiliation_strings":["Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]},{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009024971","display_name":"Teham Bhuiyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Teham Bhuiyan","raw_affiliation_strings":["Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]},{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002499102","display_name":"Jens Lambrecht","orcid":"https://orcid.org/0000-0002-1017-9548"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]},{"id":"https://openalex.org/I4210148503","display_name":"Fraunhofer Institute for Production Systems and Design Technology","ror":"https://ror.org/045eg9c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210148503","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lambrecht","raw_affiliation_strings":["Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Berlin Institute of Technology,Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science,Berlin,Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]},{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Faculty of Electrical Engineering, and Computer Science, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044968499"],"corresponding_institution_ids":["https://openalex.org/I4210148503","https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18461612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"30","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9979000091552734,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8099944591522217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7129034996032715},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.6704339981079102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5739379525184631},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4574134051799774},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4508979320526123},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4490419924259186},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.4220653772354126},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.41173139214515686},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.22861328721046448}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8099944591522217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129034996032715},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.6704339981079102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5739379525184631},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4574134051799774},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4508979320526123},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4490419924259186},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.4220653772354126},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.41173139214515686},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.22861328721046448},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cis-ram55796.2023.10370762","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cis-ram55796.2023.10370762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM)","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":20,"referenced_works":["https://openalex.org/W2104332709","https://openalex.org/W2296073425","https://openalex.org/W2890001928","https://openalex.org/W2962917939","https://openalex.org/W2963129648","https://openalex.org/W2964214518","https://openalex.org/W2964319688","https://openalex.org/W2967452881","https://openalex.org/W2969277962","https://openalex.org/W3009593063","https://openalex.org/W3129678734","https://openalex.org/W3202169896","https://openalex.org/W3205884910","https://openalex.org/W3207293238","https://openalex.org/W4200004515","https://openalex.org/W4285222628","https://openalex.org/W4300799055","https://openalex.org/W4309869955","https://openalex.org/W6740801417","https://openalex.org/W6847056214"],"related_works":["https://openalex.org/W3012552522","https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2782776446","https://openalex.org/W3043170174","https://openalex.org/W2155948905"],"abstract_inverted_index":{"In":[0,26,80],"recent":[1,27],"years,":[2,28],"Deep":[3],"Reinforcement":[4],"learning":[5],"has":[6],"made":[7],"remarkable":[8],"progress":[9],"in":[10,127,152,166,176],"various":[11,29],"application":[12],"areas":[13],"such":[14,47,99],"as":[15,48,100,131,133],"control":[16],"of":[17,38,43,77,89,92,118,120,129,157,171,178],"robots":[18,46],"and":[19,22,45,63,73,85,107,147],"vehicles,":[20],"simulation,":[21],"natural":[23],"language":[24],"processing.":[25],"research":[30],"works":[31],"applied":[32],"DRL":[33,57,78,97,125,179],"to":[34,67,123],"conduct":[35],"different":[36],"kinds":[37],"tasks":[39],"for":[40,96,110,155,181],"autonomous":[41,111,182],"navigation":[42,183],"vehicles":[44],"lane":[49],"changing,":[50],"cruise":[51],"control,":[52],"or":[53],"obstacle":[54,112],"avoidance.":[55,113],"However,":[56],"training":[58,69],"is":[59],"still":[60],"a":[61,90],"tedious":[62],"difficult":[64],"process":[65],"due":[66],"long":[68],"times,":[70],"catastrophic":[71],"forgetfulness":[72],"the":[74,87,116,124],"myopic":[75],"nature":[76],"agents.":[79],"this":[81,172],"paper,":[82],"we":[83,148],"integrate":[84],"explore":[86],"effect":[88,117],"variety":[91],"state-of-the-art":[93],"optimization":[94,162],"approaches":[95,143,163,180],"agents":[98,138],"imitation":[101],"learning,":[102],"behavior":[103],"cloning,":[104],"frame":[105],"stacking,":[106],"hindsight":[108],"replay":[109],"We":[114],"evaluate":[115],"each":[119],"these":[121,158],"changes":[122],"agent":[126],"terms":[128],"training-":[130],"well":[132],"navigational":[134,153],"performance.":[135],"The":[136,169],"resulting":[137],"are":[139],"compared":[140],"against":[141],"baseline":[142],"without":[144],"those":[145],"optimizations":[146],"found":[149],"an":[150],"increase":[151],"performance":[154],"some":[156],"methods":[159],"while":[160],"other":[161],"surprisingly":[164],"resulted":[165],"decreased":[167],"performing.":[168],"findings":[170],"paper":[173],"should":[174],"aid":[175],"development":[177],"approaches.":[184]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}