{"id":"https://openalex.org/W4413979212","doi":"https://doi.org/10.1109/rcar65431.2025.11139393","title":"Improving Stability and Efficiency of Reinforcement Learning using Reward Functions based on Lyapunov Neural Networks","display_name":"Improving Stability and Efficiency of Reinforcement Learning using Reward Functions based on Lyapunov Neural Networks","publication_year":2025,"publication_date":"2025-06-01","ids":{"openalex":"https://openalex.org/W4413979212","doi":"https://doi.org/10.1109/rcar65431.2025.11139393"},"language":"en","primary_location":{"id":"doi:10.1109/rcar65431.2025.11139393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar65431.2025.11139393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5057139947","display_name":"Mingyu Sun","orcid":"https://orcid.org/0000-0002-9090-1421"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingyu Sun","raw_affiliation_strings":["Southern University of Science and Technology,College of Engineering,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,College of Engineering,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108866869","display_name":"Chenyang Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Miao","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689058","display_name":"Yidong Chen","orcid":"https://orcid.org/0000-0002-0243-7228"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Chen","raw_affiliation_strings":["Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091902960","display_name":"Tianfu Sun","orcid":"https://orcid.org/0000-0002-5518-0315"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfu Sun","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057139947"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35692349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.609499990940094,"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"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.609499990940094,"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/T10320","display_name":"Neural Networks and Applications","score":0.5410000085830688,"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":0.7690832614898682},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6656877994537354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6399946808815002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6381396651268005},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5891541242599487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46005484461784363},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.435954749584198},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.430833101272583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2907876968383789},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18416351079940796},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13064178824424744},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.11102339625358582},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05284467339515686}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7690832614898682},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6656877994537354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6399946808815002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381396651268005},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5891541242599487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46005484461784363},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.435954749584198},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.430833101272583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2907876968383789},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18416351079940796},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13064178824424744},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.11102339625358582},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05284467339515686},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar65431.2025.11139393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar65431.2025.11139393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2001009060","https://openalex.org/W2058935279","https://openalex.org/W2133354309","https://openalex.org/W2915117209","https://openalex.org/W2990747716","https://openalex.org/W3038180127","https://openalex.org/W3110506085","https://openalex.org/W3112388352","https://openalex.org/W3157410348","https://openalex.org/W3172347396","https://openalex.org/W4221110788","https://openalex.org/W4312838995","https://openalex.org/W4317383145","https://openalex.org/W4377695283","https://openalex.org/W4402402057","https://openalex.org/W4404294040","https://openalex.org/W4406539056"],"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":{"Reinforcement":[0,27],"Learning":[1,28],"(RL)":[2],"has":[3],"demonstrated":[4],"remarkable":[5],"success":[6],"but":[7],"faces":[8],"challenges":[9],"in":[10,90,111],"stability":[11,34,104],"and":[12,41,62,88,93],"safety.":[13],"This":[14,96],"paper":[15],"introduces":[16],"DroQ_LyNN":[17,82],"that":[18],"integrates":[19],"Lyapunov":[20,33,54,103],"Neural":[21],"Networks":[22],"into":[23,65],"the":[24,36,46,66,99],"Doubly":[25],"Efficient":[26],"(DroQ)":[29],"framework.":[30],"By":[31],"leveraging":[32],"theory,":[35],"proposed":[37],"method":[38],"ensures":[39],"safe":[40,59,109],"stable":[42,70],"control":[43,94],"while":[44],"maintaining":[45],"efficiency":[47,92],"of":[48,101],"DroQ.":[49],"We":[50],"design":[51],"a":[52],"data-driven":[53],"neural":[55],"networks":[56],"to":[57],"estimate":[58],"regions":[60],"(ROA)":[61],"embed":[63],"these":[64],"reward":[67],"function,":[68],"enabling":[69],"policy":[71],"learning":[72,91,110],"without":[73],"compromising":[74],"exploration.":[75],"Experiments":[76],"on":[77],"OpenAI":[78],"safety":[79],"benchmarks":[80],"show":[81],"outperforms":[83],"baselines":[84],"like":[85],"DroQ,":[86],"TD3,":[87],"DDPGLag":[89],"stability.":[95],"work":[97],"highlights":[98],"potential":[100],"combining":[102],"with":[105],"RL":[106],"for":[107],"robust,":[108],"complex":[112],"environments.The":[113],"project":[114],"is":[115],"available":[116],"at:":[117],"https://github.com/needtorch/security-restrictions-LyNN.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}