{"id":"https://openalex.org/W4389665901","doi":"https://doi.org/10.1109/iros55552.2023.10342288","title":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning","display_name":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665901","doi":"https://doi.org/10.1109/iros55552.2023.10342288"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5079281987","display_name":"Nick B\u00fchrer","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Nick B\u00fchrer","raw_affiliation_strings":["ETH Zurich,Computer Vision Lab,Switzerland","Computer Vision Lab, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Computer Vision Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Computer Vision Lab, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102818662","display_name":"Zhejun Zhang","orcid":"https://orcid.org/0000-0002-8785-4644"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zhejun Zhang","raw_affiliation_strings":["ETH Zurich,Computer Vision Lab,Switzerland","Computer Vision Lab, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Computer Vision Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Computer Vision Lab, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048742998","display_name":"Alexander Liniger","orcid":"https://orcid.org/0000-0002-7858-7900"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alexander Liniger","raw_affiliation_strings":["ETH Zurich,Computer Vision Lab,Switzerland","Computer Vision Lab, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Computer Vision Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Computer Vision Lab, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067487326","display_name":"Fisher Yu","orcid":"https://orcid.org/0000-0001-8829-7344"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fisher Yu","raw_affiliation_strings":["ETH Zurich,Computer Vision Lab,Switzerland","Computer Vision Lab, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Computer Vision Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Computer Vision Lab, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001254143","display_name":"Luc Van Gool","orcid":"https://orcid.org/0000-0002-3445-5711"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["BE","CH"],"is_corresponding":false,"raw_author_name":"Luc Van Gool","raw_affiliation_strings":["ETH Zurich,Computer Vision Lab,Switzerland","Computer Vision Lab, ETH Zurich, Switzerland","PSI, KU Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,Computer Vision Lab,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Computer Vision Lab, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"PSI, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079281987"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67372159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5582","last_page":"5589"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.978600025177002,"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":0.8582009077072144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891640424728394},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6751200556755066},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6314961910247803},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5588518381118774},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.533315122127533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5142678618431091},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5011587142944336},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4918327331542969},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46328845620155334},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4623926877975464},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42302852869033813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14029067754745483},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10176080465316772}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8582009077072144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891640424728394},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6751200556755066},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6314961910247803},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5588518381118774},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.533315122127533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142678618431091},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5011587142944336},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4918327331542969},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46328845620155334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4623926877975464},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42302852869033813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14029067754745483},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10176080465316772},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":47,"referenced_works":["https://openalex.org/W1669104078","https://openalex.org/W2101075098","https://openalex.org/W2167340365","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2963525569","https://openalex.org/W2966735560","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2998619042","https://openalex.org/W3007196997","https://openalex.org/W3068678661","https://openalex.org/W3094224934","https://openalex.org/W3142005321","https://openalex.org/W3162902207","https://openalex.org/W3164473225","https://openalex.org/W3164515101","https://openalex.org/W3176452384","https://openalex.org/W3182751084","https://openalex.org/W3189576409","https://openalex.org/W3193987867","https://openalex.org/W3208941764","https://openalex.org/W4205430897","https://openalex.org/W4206497039","https://openalex.org/W4281480521","https://openalex.org/W4285600796","https://openalex.org/W4287629996","https://openalex.org/W4294555834","https://openalex.org/W4297824337","https://openalex.org/W4298857966","https://openalex.org/W4307572631","https://openalex.org/W6627932998","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6747473740","https://openalex.org/W6751725685","https://openalex.org/W6770009701","https://openalex.org/W6771280675","https://openalex.org/W6772456302","https://openalex.org/W6779812412","https://openalex.org/W6780587392","https://openalex.org/W6785187516","https://openalex.org/W6796690604","https://openalex.org/W6796910599","https://openalex.org/W6800776581","https://openalex.org/W6811221485"],"related_works":["https://openalex.org/W4318195686","https://openalex.org/W2975999359","https://openalex.org/W3119693376","https://openalex.org/W4306904969","https://openalex.org/W2796561647","https://openalex.org/W4280497496","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"An":[0],"emerging":[1],"field":[2],"of":[3,65,79],"sequential":[4],"decision":[5],"problems":[6],"is":[7,15,29],"safe":[8,54],"Reinforcement":[9],"Learning":[10],"(RL),":[11],"where":[12,38,155],"the":[13,18,43,46,77,84,97,151],"objective":[14],"to":[16,26,101,161],"maximize":[17],"reward":[19,71,85],"while":[20],"obeying":[21],"safety":[22,67,74,134],"constraints.":[23],"Being":[24],"able":[25],"handle":[27],"constraints":[28,135],"essential":[30],"for":[31],"deploying":[32],"RL":[33,56,112,130],"agents":[34],"in":[35,124],"real-world":[36],"environments,":[37,127],"constraint":[39,80],"violations":[40],"can":[41,169],"harm":[42],"agent":[44],"and":[45,69,82,117,120,136,142],"environment.":[47],"To":[48],"this":[49],"end,":[50],"we":[51,95,149],"propose":[52],"a":[53,59,66,70,156,164],"model-free":[55],"algorithm":[57],"with":[58,133,140],"novel":[60],"multiplicative":[61],"value":[62],"function":[63],"consisting":[64],"critic":[68,75,86],"critic.":[72],"The":[73],"predicts":[76],"probability":[78],"violation":[81],"discounts":[83],"that":[87],"only":[88],"estimates":[89],"constraint-free":[90],"returns.":[91],"By":[92],"splitting":[93],"responsibilities,":[94],"facilitate":[96],"learning":[98],"task":[99],"leading":[100],"increased":[102],"sample":[103],"efficiency.":[104],"We":[105],"integrate":[106],"our":[107,122],"approach":[108],"into":[109],"two":[110],"popular":[111],"algorithms,":[113],"Proximal":[114],"Policy":[115],"Optimization":[116],"Soft":[118],"Actor-Critic,":[119],"evaluate":[121],"method":[123],"four":[125],"safety-focused":[126],"including":[128],"classical":[129],"benchmarks":[131],"augmented":[132],"robot":[137,159],"navigation":[138],"tasks":[139],"images":[141],"raw":[143],"Lidar":[144],"scans":[145],"as":[146],"observations.":[147],"Finally,":[148],"make":[150],"zero-shot":[152],"sim-to-real":[153],"transfer":[154],"differential":[157],"drive":[158],"has":[160],"navigate":[162],"through":[163],"cluttered":[165],"room.":[166],"Our":[167],"code":[168],"be":[170],"found":[171],"at":[172],"https://github.com/nikeke19/Safe-Mult-RL.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}