{"id":"https://openalex.org/W4413393791","doi":"https://doi.org/10.23919/acc63710.2025.11107744","title":"Learning Nash Equilibrial Hamiltonian for Two-Player Collision-Avoiding Interactions","display_name":"Learning Nash Equilibrial Hamiltonian for Two-Player Collision-Avoiding Interactions","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393791","doi":"https://doi.org/10.23919/acc63710.2025.11107744"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107744","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/A5070346662","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-0096-7073"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108051741","display_name":"S. Das","orcid":"https://orcid.org/0000-0001-6857-966X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Das","raw_affiliation_strings":["Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026630117","display_name":"Tanner Merry","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanner Merry","raw_affiliation_strings":["Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040944809","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0000-0002-9654-260X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenlong Zhang","raw_affiliation_strings":["Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812349","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0003-2306-5993"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Engineering, Matter, Transport, and Energy,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070346662"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19996283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9603999853134155,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9591000080108643,"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/collision","display_name":"Collision","score":0.6429510712623596},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6307799816131592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.581032395362854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25753670930862427},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.22691425681114197},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.21284720301628113}],"concepts":[{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.6429510712623596},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6307799816131592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.581032395362854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25753670930862427},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.22691425681114197},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.21284720301628113}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107744","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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":18,"referenced_works":["https://openalex.org/W153353184","https://openalex.org/W1550828720","https://openalex.org/W2010142289","https://openalex.org/W2040294382","https://openalex.org/W2116364955","https://openalex.org/W2906904540","https://openalex.org/W2959078751","https://openalex.org/W3023371261","https://openalex.org/W3034781633","https://openalex.org/W3080564557","https://openalex.org/W3089576059","https://openalex.org/W3129637124","https://openalex.org/W3205025130","https://openalex.org/W3205626500","https://openalex.org/W3206190169","https://openalex.org/W4312581497","https://openalex.org/W4383108404","https://openalex.org/W4399511537"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W3113932901","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W650625605","https://openalex.org/W2376932109"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,15,32,38,52,84,112,122,149,153,156,168,177,187,190],"problem":[3],"of":[4,18,34,72,86,97,102,155,176],"learning":[5,96,143],"Nash":[6],"equilibrial":[7],"policies":[8,75],"for":[9,55],"two-player":[10],"risk-sensitive":[11],"collision-avoiding":[12],"interactions.":[13],"Solving":[14],"Hamilton-Jacobi-Isaacs":[16],"equations":[17],"such":[19],"general-sum":[20],"differential":[21],"games":[22],"in":[23,80,181],"real":[24],"time":[25],"is":[26,44,64,129],"an":[27,164],"open":[28],"challenge":[29],"due":[30],"to":[31,45,82,136,144,159,172],"discontinuity":[33],"equilibrium":[35,53,74,98,113,178],"values":[36],"on":[37],"state":[39],"space.":[40],"A":[41],"common":[42],"solution":[43],"learn":[46],"a":[47,69,106],"neural":[48],"network":[49],"that":[50,111],"approximates":[51],"Hamiltonian":[54,104],"given":[56],"system":[57,127],"states":[58,79],"and":[59,67,126,131,180],"actions.":[60],"The":[61],"learning,":[62],"however,":[63],"usually":[65],"supervised":[66],"requires":[68],"large":[70],"amount":[71],"sample":[73],"from":[76],"different":[77],"initial":[78],"order":[81],"mitigate":[83],"risks":[85],"collisions.":[87],"This":[88],"paper":[89],"claims":[90],"two":[91],"contributions":[92],"towards":[93],"more":[94,134,173],"data-efficient":[95,135],"policies:":[99],"First,":[100],"instead":[101],"computing":[103],"through":[105],"value":[107],"network,":[108],"we":[109,139],"show":[110],"co-states":[114,158],"have":[115],"simple":[116],"structures":[117],"when":[118],"collision":[119,184],"avoidance":[120],"dominates":[121],"agents\u2019":[123],"loss":[124],"functions":[125],"dynamics":[128],"linear,":[130],"therefore":[132],"are":[133],"learn.":[137],"Second,":[138],"introduce":[140],"theory-driven":[141],"active":[142],"guide":[145],"data":[146,192],"sampling,":[147],"where":[148],"acquisition":[150,193],"function":[151],"measures":[152],"compliance":[154],"predicted":[157],"Pontryagin\u2019s":[160],"Maximum":[161],"Principle.":[162],"On":[163],"uncontrolled":[165],"intersection":[166],"case,":[167],"proposed":[169],"method":[170],"leads":[171],"generalizable":[174],"approximation":[175],"policies,":[179],"turn,":[182],"lower":[183],"probabilities,":[185],"than":[186],"state-of-the-art":[188],"under":[189],"same":[191],"budget.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}