{"id":"https://openalex.org/W4414359379","doi":"https://doi.org/10.24963/ijcai.2025/592","title":"Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning","display_name":"Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359379","doi":"https://doi.org/10.24963/ijcai.2025/592"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/592","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5021957449","display_name":"Somnath Hazra","orcid":"https://orcid.org/0000-0003-1497-1820"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Somnath Hazra","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033329960","display_name":"Pallab Dasgupta","orcid":"https://orcid.org/0000-0002-2178-8154"},"institutions":[{"id":"https://openalex.org/I4210088951","display_name":"Synopsys (United States)","ror":"https://ror.org/013by2m91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088951"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pallab Dasgupta","raw_affiliation_strings":["Synopsys, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Synopsys, USA","institution_ids":["https://openalex.org/I4210088951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085224640","display_name":"Soumyajit Dey","orcid":"https://orcid.org/0000-0001-9329-6389"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumyajit Dey","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38196864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5318","last_page":"5326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.7628999948501587,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.7628999948501587,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.692300021648407,"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":0.7949000000953674},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6421999931335449},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.5414999723434448},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5340999960899353},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5303000211715698},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5080999732017517},{"id":"https://openalex.org/keywords/constraint-learning","display_name":"Constraint learning","score":0.40459999442100525},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40059998631477356},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.37450000643730164}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7949000000953674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802999973297119},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6421999931335449},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.5414999723434448},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C29230964","wikidata":"https://www.wikidata.org/wiki/Q5164376","display_name":"Constraint learning","level":5,"score":0.40459999442100525},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C153517567","wikidata":"https://www.wikidata.org/wiki/Q26090","display_name":"Mechanism design","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C6180225","wikidata":"https://www.wikidata.org/wiki/Q3411771","display_name":"Penalty method","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C34432948","wikidata":"https://www.wikidata.org/wiki/Q7140428","display_name":"Participation constraint","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C176783269","wikidata":"https://www.wikidata.org/wiki/Q5164378","display_name":"Constraint logic programming","level":4,"score":0.2727999985218048},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/592","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Constrained":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"aims":[4],"to":[5,11,74,78,110,127],"maximize":[6],"the":[7,31,75,81,86,122,128,145,149],"return":[8],"while":[9],"adhering":[10],"predefined":[12],"constraint":[13,37,50,82,87],"limits,":[14],"which":[15],"represent":[16],"domain-specific":[17],"safety":[18],"requirements.":[19],"In":[20],"continuous":[21],"control":[22],"settings,":[23],"where":[24],"learning":[25],"agents":[26],"govern":[27],"system":[28],"actions,":[29],"balancing":[30],"trade-off":[32],"between":[33],"reward":[34,76],"maximization":[35],"and":[36],"satisfaction":[38],"remains":[39],"a":[40,63,101,106,142],"significant":[41],"challenge.":[42],"Policy":[43,98],"optimization":[44],"methods":[45],"often":[46],"exhibit":[47],"instability":[48],"near":[49],"boundaries,":[51],"resulting":[52],"in":[53,72],"suboptimal":[54],"training":[55,112],"performance.":[56],"To":[57],"address":[58],"this":[59,91],"issue,":[60],"we":[61,93,120,136],"introduce":[62],"novel":[64],"approach":[65],"that":[66,104],"integrates":[67],"an":[68],"adaptive":[69],"incentive":[70],"mechanism":[71],"addition":[73],"structure":[77],"stay":[79],"within":[80],"bound":[83,143],"before":[84],"approaching":[85],"boundary.":[88],"Building":[89],"on":[90,117,144],"insight,":[92],"propose":[94],"Incrementally":[95],"Penalized":[96],"Proximal":[97],"Optimization":[99],"(IP3O),":[100],"practical":[102],"algorithm":[103],"enforces":[105],"progressively":[107],"increasing":[108],"penalty":[109],"stabilize":[111],"dynamics.":[113],"Through":[114],"empirical":[115],"evaluation":[116],"benchmark":[118],"environments,":[119],"demonstrate":[121],"efficacy":[123],"of":[124,130,148],"IP3O":[125],"compared":[126],"performance":[129],"state-of-the-art":[131],"Safe":[132],"RL":[133],"algorithms.":[134],"Furthermore,":[135],"provide":[137],"theoretical":[138],"guarantees":[139],"by":[140,152],"deriving":[141],"worst-case":[146],"error":[147],"optimality":[150],"achieved":[151],"our":[153],"algorithm.":[154]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}