{"id":"https://openalex.org/W4390532423","doi":"https://doi.org/10.1145/3632410.3632446","title":"Model-based Safe Reinforcement Learning using Variable Horizon Rollouts","display_name":"Model-based Safe Reinforcement Learning using Variable Horizon Rollouts","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390532423","doi":"https://doi.org/10.1145/3632410.3632446"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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/A5060216948","display_name":"Subrata Roy Gupta","orcid":"https://orcid.org/0009-0009-5825-2394"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shourya Gupta","raw_affiliation_strings":["Indian Institute of Technology Ropar, India"],"raw_orcid":"https://orcid.org/0009-0009-5825-2394","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093643175","display_name":"Utkarsh Suryaman","orcid":"https://orcid.org/0009-0005-0869-7193"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Utkarsh Suryaman","raw_affiliation_strings":["Indian Institute of Technology Ropar, India"],"raw_orcid":"https://orcid.org/0009-0005-0869-7193","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093643176","display_name":"Rahul Narava","orcid":"https://orcid.org/0009-0009-0277-4484"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rahul Narava","raw_affiliation_strings":["Indian Institute of Technology Ropar, India"],"raw_orcid":"https://orcid.org/0009-0009-0277-4484","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003320528","display_name":"Shashi Shekhar Jha","orcid":"https://orcid.org/0000-0002-1375-2266"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashi Shekhar Jha","raw_affiliation_strings":["Indian Institute of Technology Ropar, India"],"raw_orcid":"https://orcid.org/0000-0002-1375-2266","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, India","institution_ids":["https://openalex.org/I119241673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060216948"],"corresponding_institution_ids":["https://openalex.org/I119241673"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00711512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9926000237464905,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9926000237464905,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9854000210762024,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.921903669834137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267088294029236},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.6334190964698792},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.607747495174408},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4520329535007477},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4476465880870819},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4313937723636627},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41957736015319824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4141707122325897},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34920430183410645},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.31420424580574036},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27559328079223633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09660443663597107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.921903669834137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267088294029236},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.6334190964698792},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.607747495174408},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4520329535007477},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4476465880870819},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4313937723636627},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41957736015319824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4141707122325897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34920430183410645},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31420424580574036},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27559328079223633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09660443663597107},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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":8,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1845972764","https://openalex.org/W2158782408","https://openalex.org/W3094224934","https://openalex.org/W3195968524","https://openalex.org/W3212961045","https://openalex.org/W4211221179","https://openalex.org/W4221161274"],"related_works":["https://openalex.org/W2906267174","https://openalex.org/W134501823","https://openalex.org/W2615656344","https://openalex.org/W2809608782","https://openalex.org/W2013239059","https://openalex.org/W2295626654","https://openalex.org/W2333245620","https://openalex.org/W4286622840","https://openalex.org/W2536121351","https://openalex.org/W1889576908"],"abstract_inverted_index":{"Safe":[0],"reinforcement":[1,17,38,61],"learning":[2,18,39,62],"aims":[3],"to":[4,49,68,76,111,147,186],"ensure":[5],"the":[6,14,46,51,54,73,90,106,113,116,121,137,153,163,190],"safety":[7,22,42,52,181],"of":[8,53,115,139,155,165,180],"agents":[9],"and":[10,98,150],"their":[11],"interactions":[12],"with":[13],"environment.":[15],"Traditional":[16],"algorithms":[19,40],"often":[20],"neglect":[21],"considerations,":[23],"resulting":[24,94],"in":[25,30,95,100,168,178],"undesirable":[26],"consequences":[27],"when":[28],"deployed":[29],"real-world":[31],"scenarios.":[32],"To":[33,125],"address":[34],"this":[35,80],"issue,":[36],"safe":[37,60],"incorporate":[41],"constraints":[43],"or":[44],"modify":[45],"reward":[47],"distribution":[48],"prioritize":[50],"agent.":[55],"Recent":[56],"literature":[57],"on":[58,89,120],"model-based":[59],"uses":[63],"a":[64,84,131,175],"fixed":[65],"look-ahead":[66,87],"horizon":[67,86,117],"avoid":[69],"unsafe":[70,148],"states,":[71],"limiting":[72],"agent\u2019s":[74,91,122],"adaptability":[75,99],"changing":[77],"environments.":[78,102,171],"In":[79],"paper,":[81],"we":[82,129],"propose":[83],"variable":[85],"based":[88,119],"current":[92,123],"state,":[93],"improved":[96],"performance":[97],"uncertain":[101],"Our":[103,172],"approach":[104,167],"leverages":[105],"Gaussian":[107],"process":[108],"regression":[109],"model":[110],"estimate":[112],"value":[114],"dynamically":[118],"state.":[124],"enhance":[126],"sample":[127],"efficiency,":[128],"introduce":[130],"selective":[132],"sampling":[133],"strategy":[134],"that":[135,144],"reduces":[136],"number":[138],"rollouts":[140],"by":[141],"eliminating":[142],"samples":[143],"may":[145],"lead":[146],"states":[149],"also":[151],"optimizes":[152],"use":[154],"computational":[156],"resources":[157],"while":[158],"ensuring":[159],"safety.":[160],"We":[161],"evaluate":[162],"effectiveness":[164],"our":[166],"multiple":[169],"mujoco":[170],"results":[173],"demonstrate":[174],"significant":[176],"reduction":[177],"terms":[179],"violations":[182],"during":[183],"validating":[184],"compared":[185],"existing":[187],"approaches":[188],"from":[189],"literature.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}