{"id":"https://openalex.org/W4416250595","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227962","title":"Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Non-equilibrium Loss Landscapes via the Fokker\u2013Planck Equation","display_name":"Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Non-equilibrium Loss Landscapes via the Fokker\u2013Planck Equation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250595","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227962"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030770267","display_name":"Shuyu Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyu Yin","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101631903","display_name":"Wen Fei","orcid":"https://orcid.org/0000-0002-1682-4480"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wen","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032986088","display_name":"Peilin Liu","orcid":"https://orcid.org/0000-0002-5321-2336"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peilin Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101767084","display_name":"T. Luo","orcid":"https://orcid.org/0000-0001-5188-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Luo","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Mathematical Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Mathematical Sciences,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.45159998536109924,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.45159998536109924,"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":0.10320000350475311,"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/T11804","display_name":"Quantum many-body systems","score":0.05920000001788139,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5702999830245972},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.48969998955726624},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4620000123977661},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.45190000534057617},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.445499986410141},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43479999899864197}],"concepts":[{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309000015258789},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38449999690055847},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3684000074863434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C196298200","wikidata":"https://www.wikidata.org/wiki/Q577705","display_name":"Critical point (mathematics)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1553308207","https://openalex.org/W1646707810","https://openalex.org/W1969477885","https://openalex.org/W1970283086","https://openalex.org/W2138710479","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2766447205","https://openalex.org/W2902175656","https://openalex.org/W2963518130","https://openalex.org/W2982316857","https://openalex.org/W3152509363","https://openalex.org/W4377941395"],"related_works":[],"abstract_inverted_index":{"Semi-gradient":[0],"Q-learning":[1],"is":[2],"widely":[3],"applied":[4],"across":[5],"various":[6],"fields;":[7],"however,":[8],"due":[9],"to":[10,38,81],"the":[11,25,28,35,42,55,98],"absence":[12],"of":[13,101],"an":[14],"explicit":[15],"loss":[16,44],"function,":[17],"understanding":[18],"its":[19],"preference":[20],"for":[21],"critical":[22,60,72],"points":[23,61],"in":[24,46,66],"parameter":[26,49,83],"space\u2014namely,":[27],"implicit":[29,99],"bias\u2014remains":[30],"challenging.":[31],"This":[32,92],"paper":[33,93],"leverages":[34],"Fokker\u2013Planck":[36],"equation":[37],"construct":[39],"and":[40,85],"visualize":[41],"non-equilibrium":[43],"landscape":[45],"a":[47],"two-dimensional":[48],"space.":[50],"Our":[51],"visualization":[52],"reveals":[53],"that":[54,77],"semi-gradient":[56,102],"method":[57],"transforms":[58],"stable":[59],"into":[62,97],"unstable":[63,71],"ones,":[64],"resulting":[65],"training":[67],"dynamics":[68],"biased":[69],"against":[70],"points.":[73],"Furthermore,":[74],"we":[75],"show":[76],"this":[78],"phenomenon":[79],"extends":[80],"high-dimensional":[82],"spaces":[84],"neural":[86],"network":[87],"settings,":[88],"such":[89],"as":[90],"DQN.":[91],"provides":[94],"valuable":[95],"insights":[96],"bias":[100],"Q-learning.":[103]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}