{"id":"https://openalex.org/W4401415617","doi":"https://doi.org/10.1109/icra57147.2024.10611554","title":"Projection-Based Fast and Safe Policy Optimization for Reinforcement Learning","display_name":"Projection-Based Fast and Safe Policy Optimization for Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415617","doi":"https://doi.org/10.1109/icra57147.2024.10611554"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611554","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100956857","display_name":"Shijun Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shijun Lin","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116592778","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-2227-075X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324492","display_name":"Ziyang Chen","orcid":"https://orcid.org/0000-0003-3077-822X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Chen","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018344952","display_name":"Zhen Kan","orcid":"https://orcid.org/0000-0003-2069-9544"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Kan","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China,230026"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China,230026","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100956857"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10598093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":null,"first_page":"7426","last_page":"7432"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10524","display_name":"Traffic control and management","score":0.9904999732971191,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8323761820793152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7333106994628906},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5638285279273987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46014416217803955},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36116692423820496},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15543845295906067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11562442779541016}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8323761820793152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333106994628906},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5638285279273987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46014416217803955},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36116692423820496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15543845295906067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11562442779541016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611554","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1972149633","https://openalex.org/W1980569135","https://openalex.org/W2070570138","https://openalex.org/W2106850246","https://openalex.org/W2165161585","https://openalex.org/W2736601468","https://openalex.org/W2804791273","https://openalex.org/W2968945909","https://openalex.org/W3003907021","https://openalex.org/W3039276491","https://openalex.org/W3094224934","https://openalex.org/W3101517963","https://openalex.org/W3103190791","https://openalex.org/W3119862069","https://openalex.org/W3166557699","https://openalex.org/W4206497039","https://openalex.org/W4206742989","https://openalex.org/W4285483697","https://openalex.org/W4306783402","https://openalex.org/W4324119916","https://openalex.org/W4385574945","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6643032878","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6751725685","https://openalex.org/W6752298494","https://openalex.org/W6771280675","https://openalex.org/W6772215039","https://openalex.org/W6779812412","https://openalex.org/W6785187516","https://openalex.org/W6785471904","https://openalex.org/W6790722625","https://openalex.org/W6838566501","https://openalex.org/W6839971674"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"While":[0],"reinforcement":[1],"learning":[2,97],"(RL)":[3],"attracts":[4],"increasing":[5],"research":[6],"attention,":[7],"maximizing":[8],"the":[9,13,17,46,53,57,60,63,68,72,76,81,85,94,108],"return":[10],"while":[11],"keeping":[12],"agent":[14],"safe":[15,129],"at":[16],"same":[18],"time":[19],"remains":[20],"an":[21],"open":[22],"problem.":[23],"Motivated":[24],"to":[25,59,66,118],"address":[26],"this":[27,29,112],"challenge,":[28],"work":[30,113],"proposes":[31],"a":[32,89,115],"new":[33],"Fast":[34],"and":[35,71,96,110,122,128,138,152],"Safe":[36],"Policy":[37],"Optimization":[38],"(FSPO)":[39],"algorithm,":[40],"which":[41],"consists":[42],"of":[43,62,149],"three":[44],"steps:":[45],"first":[47],"step":[48,55,74],"involves":[49],"reward":[50],"improvement":[51],"update,":[52],"second":[54],"projects":[56],"policy":[58,65,82,130],"neighborhood":[61],"baseline":[64],"accelerate":[67],"optimization":[69,91],"process,":[70],"third":[73],"addresses":[75],"constraint":[77,86],"violation":[78],"by":[79],"projecting":[80],"back":[83],"onto":[84],"set.":[87],"Such":[88],"projection-based":[90],"can":[92],"improve":[93],"convergence":[95],"performance.":[98],"Unlike":[99],"many":[100],"existing":[101,145],"works":[102],"that":[103,142],"require":[104],"convex":[105],"approximations":[106],"for":[107,133],"objectives":[109],"constraints,":[111],"exploits":[114],"first-order":[116],"method":[117],"avoid":[119],"expensive":[120],"computations":[121],"high":[123],"dimensional":[124],"issues,":[125],"enabling":[126],"fast":[127],"optimization,":[131],"especially":[132],"challenging":[134],"tasks.":[135],"Numerical":[136],"simulation":[137],"physical":[139],"experiments":[140],"demonstrate":[141],"FSPO":[143],"outperforms":[144],"methods":[146],"in":[147],"terms":[148],"safety":[150],"guarantees":[151],"task":[153],"completion":[154],"rate.":[155]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}