{"id":"https://openalex.org/W7225751935","doi":"https://doi.org/10.21203/rs.3.rs-11657377/v1","title":"When Local Credit Assignment Breaks: Exact Diagnostics of Additive and Pairwise Reward Projection","display_name":"When Local Credit Assignment Breaks: Exact Diagnostics of Additive and Pairwise Reward Projection","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225751935","doi":"https://doi.org/10.21203/rs.3.rs-11657377/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11657377/v1","doi":"https://doi.org/10.21203/rs.3.rs-11657377/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11657377/v1","pdf_url":"https://www.researchsquare.com/article/rs-11657377/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11657377/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161393065","display_name":"Krishna Varun Kasamneni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Krishna Varun Kasamneni","raw_affiliation_strings":["Independent researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161393065"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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/T11031","display_name":"Game Theory and Applications","score":0.0,"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":[],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8001000285148621},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7477999925613403},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5554999709129333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5534999966621399},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3790999948978424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11657377/v1","doi":"https://doi.org/10.21203/rs.3.rs-11657377/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11657377/v1","pdf_url":"https://www.researchsquare.com/article/rs-11657377/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11657377/v1","doi":"https://doi.org/10.21203/rs.3.rs-11657377/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11657377/v1","pdf_url":"https://www.researchsquare.com/article/rs-11657377/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225751935.pdf","grobid_xml":"https://content.openalex.org/works/W7225751935.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3201284849","https://openalex.org/W7126271080"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Average":[1],"reward":[2,144],"reconstruction":[3,75,125],"error":[4,56,76,153],"is":[5,132,138,146],"an":[6,165],"incomplete":[7],"measure":[8],"of":[9,13,25,71,183],"the":[10,47,79,91,100,106,115,120,149],"decision":[11],"quality":[12],"a":[14,20,31,38,43,155,180],"factored":[15],"cooperative":[16],"model.":[17],"We":[18],"provide":[19],"small,":[21],"fully":[22],"reproducible":[23],"diagnostic":[24],"this":[26],"established":[27,166],"issue,":[28],"rather":[29],"than":[30],"new":[32,181],"multi-agent":[33],"reinforcement":[34],"learning":[35],"algorithm.":[36],"In":[37],"binary":[39],"one-step":[40],"game":[41],"with":[42],"rare":[44],"joint":[45],"synergy,":[46],"exact":[48],"uniform":[49,124],"least-squares":[50],"additive":[51,130],"projection":[52,108],"has":[53],"mean":[54],"squared":[55],"2\u207b\u207f":[57],"\u2212":[58,66],"(n":[59],"+":[60],"1)4\u207b\u207f":[61],"but":[62],"coordination":[63],"regret":[64,137],"1":[65],"3n2\u207b\u207f.":[67],"Adding":[68],"any":[69],"set":[70],"pairwise":[72],"factors":[73],"reduces":[74],"without":[77],"changing":[78],"wrong":[80],"maximizing":[81],"action.":[82],"Exhaustive":[83],"evaluation":[84],"at":[85],"up":[86],"to":[87],"16":[88,128],"agents":[89],"confirms":[90],"formulas;":[92],"800":[93],"independent":[94],"sampled":[95],"fits":[96],"illustrate":[97],"that":[98],"observing":[99],"synergistic":[101],"action":[102,118],"need":[103],"not":[104,175],"repair":[105],"population":[107],"objective.":[109],"A":[110],"privileged":[111],"twofold":[112],"weight":[113],"on":[114],"known":[116],"optimal":[117],"reverses":[119],"policy":[121],"while":[122],"increasing":[123],"error.":[126],"At":[127],"agents,":[129],"MSE":[131,141],"1.52548":[133],"\u00d7":[134],"10\u207b\u2075":[135],"and":[136,171],"0.999268.":[139],"However,":[140],"divided":[142],"by":[143],"variance":[145],"0.999939,":[147],"exposing":[148],"apparently":[150],"small":[151],"absolute":[152],"as":[154],"sparse-reward":[156],"averaging":[157],"effect.":[158],"The":[159],"package":[160],"supplies":[161],"proofs,":[162],"controlled":[163],"ablations,":[164],"matrix-game":[167],"check,":[168],"raw":[169],"results,":[170],"tests.":[172],"It":[173],"does":[174],"reproduce":[176],"LOMAQ":[177],"or":[178],"establish":[179],"failure":[182],"neural":[184],"value-decomposition":[185],"algorithms.":[186]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}