{"id":"https://openalex.org/W3036741195","doi":null,"title":"Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer.","display_name":"Set-Invariant Constrained Reinforcement Learning with a Meta-Optimizer.","publication_year":2020,"publication_date":"2020-06-19","ids":{"openalex":"https://openalex.org/W3036741195","mag":"3036741195"},"language":"en","primary_location":{"id":"mag:3036741195","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.11419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.11419","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051533554","display_name":"Chuangchuang Sun","orcid":"https://orcid.org/0000-0003-3049-5828","observed_orcids":["https://orcid.org/0000-0003-3049-5828"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuangchuang Sun","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3049-5828","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Ki Kim","orcid":"https://orcid.org/0000-0002-5195-7852","observed_orcids":["https://orcid.org/0000-0002-5195-7852"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Ki Kim","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5195-7852","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930","observed_orcids":["https://orcid.org/0000-0001-8576-1930"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8576-1930","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0010999999940395355,"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/T10791","display_name":"Advanced Control Systems Optimization","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/constrained-reinforcement-learning","display_name":"constrained reinforcement learning","score":0.9559999704360962},{"id":"https://openalex.org/keywords/safety-critical-systems","display_name":"safety-critical systems","score":0.6840000152587891},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.9409999847412109},{"id":"https://openalex.org/keywords/polytope-projection","display_name":"polytope projection","score":0.8479999899864197},{"id":"https://openalex.org/keywords/constraint-violation","display_name":"constraint violation","score":0.5339999794960022},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6236041188240051},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6060882210731506},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6045154333114624},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5654557347297668},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.5421465635299683},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5290783047676086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5168319344520569},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.49074944853782654},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4827386736869812},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4653265178203583},{"id":"https://openalex.org/C177067428","wikidata":"https://www.wikidata.org/wiki/Q17013331","display_name":"Feasible region","level":2,"score":0.428347110748291},{"id":"https://openalex.org/C145691206","wikidata":"https://www.wikidata.org/wiki/Q747980","display_name":"Polytope","level":2,"score":0.4199882745742798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3219463527202606},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2011130154132843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17412236332893372},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3036741195","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.11419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3036741195","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.11419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1522301498","https://openalex.org/W1532854728","https://openalex.org/W1845972764","https://openalex.org/W1880805667","https://openalex.org/W1985123706","https://openalex.org/W2093229781","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2171505650","https://openalex.org/W2560504659","https://openalex.org/W2575705757","https://openalex.org/W2616964725","https://openalex.org/W2624086852","https://openalex.org/W2742093937","https://openalex.org/W2751422670","https://openalex.org/W2784465508","https://openalex.org/W2803543472","https://openalex.org/W2900127069","https://openalex.org/W2951634833","https://openalex.org/W2952337742","https://openalex.org/W2963082979","https://openalex.org/W2963184621","https://openalex.org/W2964161785","https://openalex.org/W2966735560","https://openalex.org/W2970927156","https://openalex.org/W2990866132","https://openalex.org/W3012839911","https://openalex.org/W3015606043","https://openalex.org/W3016534272","https://openalex.org/W3041244724","https://openalex.org/W3098428275","https://openalex.org/W3141595720"],"related_works":["https://openalex.org/W3206448035","https://openalex.org/W3096475008","https://openalex.org/W3036821294","https://openalex.org/W7135065186","https://openalex.org/W7081581086","https://openalex.org/W3210035896","https://openalex.org/W2889696653","https://openalex.org/W4221144246","https://openalex.org/W7119795638","https://openalex.org/W7162249893"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"reinforcement":[3],"learning":[4],"with":[5,115],"constraints,":[6,109],"which":[7,110],"is":[8,47,97],"indispensable":[9],"in":[10,49],"safety-critical":[11],"environments.":[12],"To":[13,75],"drive":[14],"the":[15,20,34,38,43,52,59,64,88,121,124,130,135,141],"constraint":[16,131],"violation":[17,132],"monotonically":[18,128],"decrease,":[19],"constraints":[21,30,55],"are":[22,31,56,71],"taken":[23],"as":[24],"Lyapunov":[25],"functions,":[26],"and":[27,133],"new":[28,53],"linear":[29,93,107],"imposed":[32,57],"on":[33,58],"updating":[35,60],"dynamics":[36,61],"of":[37,63],"policy":[39,66,125],"parameters":[40],"such":[41,92],"that":[42],"original":[44,65],"safety":[45],"set":[46],"forward-invariant":[48],"expectation.":[50],"As":[51],"guaranteed-feasible":[54],"instead":[62],"parameters,":[67],"classic":[68],"optimization":[69],"algorithms":[70],"no":[72],"longer":[73],"applicable.":[74],"address":[76],"this,":[77],"we":[78],"propose":[79],"to":[80,86,127],"learn":[81],"a":[82,102],"neural":[83],"network-based":[84],"meta-optimizer":[85,122],"optimize":[87],"objective":[89],"while":[90],"satisfying":[91],"constraints.":[94],"The":[95],"constraint-satisfaction":[96],"achieved":[98],"via":[99],"projection":[100],"onto":[101],"polytope":[103],"formulated":[104],"by":[105],"multiple":[106],"inequality":[108],"can":[111],"be":[112],"solved":[113],"analytically":[114],"our":[116],"newly":[117],"designed":[118],"metric.":[119],"Ultimately,":[120],"trains":[123],"network":[126],"decrease":[129],"maximize":[134],"cumulative":[136],"reward.":[137],"Numerical":[138],"results":[139],"validate":[140],"theoretical":[142],"findings.":[143]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-06-25T00:00:00"}