{"id":"https://openalex.org/W3207095241","doi":"https://doi.org/10.1109/icra48506.2021.9562026","title":"Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture","display_name":"Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207095241","doi":"https://doi.org/10.1109/icra48506.2021.9562026","mag":"3207095241"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9562026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9562026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100907541","display_name":"Chin\u2010Jui Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chin-Jui Chang","raw_affiliation_strings":["Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108710867","display_name":"Yu-Wei Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Wei Chu","raw_affiliation_strings":["Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059182914","display_name":"Chao-Hsien Ting","orcid":"https://orcid.org/0000-0003-1237-0087"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Hsien Ting","raw_affiliation_strings":["Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053921126","display_name":"Hao-Kang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hao-Kang Liu","raw_affiliation_strings":["Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017776857","display_name":"Zhang-Wei Hong","orcid":"https://orcid.org/0000-0001-8574-6108"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zhang-Wei Hong","raw_affiliation_strings":["Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028600832","display_name":"Chun\u2010Yi Lee","orcid":"https://orcid.org/0000-0002-4680-4800"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Yi Lee","raw_affiliation_strings":["Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Elsa Lab, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100907541"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55870513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"529","issue":null,"first_page":"4762","last_page":"4768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9775000214576721,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8047571182250977},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.781808614730835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7190489172935486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134947776794434},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6955509185791016},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4896388649940491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4883274734020233},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3841937184333801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3305267095565796},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15529665350914001}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8047571182250977},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.781808614730835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7190489172935486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134947776794434},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6955509185791016},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4896388649940491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4883274734020233},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3841937184333801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3305267095565796},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15529665350914001},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9562026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9562026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309618","display_name":"Ministry of Science and Technology","ror":"https://ror.org/02b207r52"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2109910161","https://openalex.org/W2134797427","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2434014514","https://openalex.org/W2523728418","https://openalex.org/W2553882142","https://openalex.org/W2575705757","https://openalex.org/W2594829461","https://openalex.org/W2604319603","https://openalex.org/W2606433045","https://openalex.org/W2612864759","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2891076394","https://openalex.org/W2949267040","https://openalex.org/W2950614095","https://openalex.org/W2963142324","https://openalex.org/W2963277051","https://openalex.org/W2963286043","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964118262","https://openalex.org/W2964227312","https://openalex.org/W2995726179","https://openalex.org/W3009593063","https://openalex.org/W3037207827","https://openalex.org/W4297669644","https://openalex.org/W4300799055","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6704665273","https://openalex.org/W6718092244","https://openalex.org/W6727349600","https://openalex.org/W6730038592","https://openalex.org/W6734215269","https://openalex.org/W6736368053","https://openalex.org/W6740801417","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6752089545","https://openalex.org/W6764125455","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"has":[4],"been":[5],"demonstrated":[6],"to":[7,35,48,98],"provide":[8],"promising":[9],"results":[10,79],"in":[11,51],"several":[12],"challenging":[13],"decision":[14],"making":[15],"and":[16,73],"control":[17,90],"tasks.":[18],"However,":[19],"the":[20,62,100,105],"required":[21],"inference":[22,64,101],"costs":[23,65,102],"of":[24,84],"deep":[25],"neural":[26],"networks":[27],"(DNNs)":[28],"could":[29],"prevent":[30],"DRL":[31,46],"from":[32],"being":[33],"applied":[34],"mobile":[36],"robots":[37],"which":[38],"cannot":[39],"afford":[40],"high":[41],"energy-consuming":[42],"computations.":[43],"To":[44],"enable":[45],"methods":[47],"be":[49],"affordable":[50],"such":[52],"energy-limited":[53],"platforms,":[54],"we":[55],"propose":[56],"an":[57,74],"asymmetric":[58],"architecture":[59],"that":[60,93],"reduces":[61],"overall":[63,107],"via":[66],"switching":[67],"between":[68],"a":[69,82],"computationally":[70],"expensive":[71],"policy":[72],"economic":[75],"one.":[76],"The":[77],"experimental":[78],"evaluated":[80],"on":[81],"number":[83],"representative":[85],"benchmark":[86],"suites":[87],"for":[88],"robotic":[89],"tasks":[91],"demonstrate":[92],"our":[94],"method":[95],"is":[96],"able":[97],"reduce":[99],"while":[103],"retaining":[104],"agent\u2019s":[106],"performance.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}