{"id":"https://openalex.org/W4281392159","doi":"https://doi.org/10.1145/3534678.3539391","title":"Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions","display_name":"Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4281392159","doi":"https://doi.org/10.1145/3534678.3539391"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539391","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.10218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057395265","display_name":"Rui Yang","orcid":"https://orcid.org/0009-0004-5137-9302"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Yang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440033","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0001-9902-5723"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Institute of Artificial Intelligence & University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence & University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088255585","display_name":"Zijie Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Geng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010835132","display_name":"Mingxuan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxuan Ye","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052278550","display_name":"Shuiwang Ji","orcid":"https://orcid.org/0000-0002-4205-4563"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuiwang Ji","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365266","display_name":"Bin Li","orcid":"https://orcid.org/0000-0003-2696-6930"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5057395265"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.3564,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82649709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2242","last_page":"2252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9957000017166138,"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/T10320","display_name":"Neural Networks and Applications","score":0.9957000017166138,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9908999800682068,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9890000224113464,"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/generalization","display_name":"Generalization","score":0.7982692718505859},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7506930828094482},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7331373691558838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6615264415740967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5570933818817139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37080150842666626},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33405399322509766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2164977490901947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09032455086708069}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7982692718505859},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7506930828094482},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7331373691558838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615264415740967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570933818817139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37080150842666626},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33405399322509766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2164977490901947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09032455086708069},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539391","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.10218","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.10218","pdf_url":"https://arxiv.org/pdf/2205.10218","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.10218","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.10218","pdf_url":"https://arxiv.org/pdf/2205.10218","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1539670134","https://openalex.org/W1968962398","https://openalex.org/W1976268573","https://openalex.org/W2032375682","https://openalex.org/W2100484755","https://openalex.org/W2154997814","https://openalex.org/W2765407302","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2810785043","https://openalex.org/W2893662673","https://openalex.org/W2947334431","https://openalex.org/W2949510923","https://openalex.org/W2996283175","https://openalex.org/W2997101648","https://openalex.org/W2997103132","https://openalex.org/W3011651653","https://openalex.org/W3021708257","https://openalex.org/W3034561250","https://openalex.org/W3036670859","https://openalex.org/W3041404693","https://openalex.org/W3094013182","https://openalex.org/W3115293622","https://openalex.org/W3125947392","https://openalex.org/W3129170303","https://openalex.org/W3169424162","https://openalex.org/W3172628684","https://openalex.org/W3176138766","https://openalex.org/W4226265052","https://openalex.org/W4255556797","https://openalex.org/W4287393217","https://openalex.org/W4287811291","https://openalex.org/W4288088584","https://openalex.org/W4289294484","https://openalex.org/W4295549420","https://openalex.org/W4297797010","https://openalex.org/W4297808394","https://openalex.org/W4388297583","https://openalex.org/W6745136726"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4200527723"],"abstract_inverted_index":{"Generalization":[0],"across":[1],"different":[2,145],"environments":[3],"with":[4,144],"the":[5,35,43,64,74,90,102,115,120,130],"same":[6],"tasks":[7,143],"is":[8],"critical":[9],"for":[10],"successful":[11],"applications":[12],"of":[13,45,105,132],"visual":[14,22,39,84,146],"reinforcement":[15],"learning":[16,68],"(RL)":[17],"in":[18,26,38,79],"real":[19,27],"scenarios.":[20],"However,":[21],"distractions---which":[23],"are":[24,77],"common":[25],"scenes---from":[28],"high-dimensional":[29,116],"observations":[30],"can":[31,112],"be":[32],"hurtful":[33],"to":[34,62,83,87],"learned":[36],"representations":[37],"RL,":[40],"thus":[41],"degrading":[42],"performance":[44,131],"generalization.":[46],"To":[47],"tackle":[48],"this":[49],"problem,":[50],"we":[51,111],"propose":[52],"a":[53],"novel":[54],"approach,":[55],"namely":[56],"Characteristic":[57],"Reward":[58],"Sequence":[59],"Prediction":[60],"(CRESP),":[61],"extract":[63],"task-relevant":[65,78,91,108],"information":[66,92],"by":[67,118],"reward":[69,75],"sequence":[70],"distributions":[71,117],"(RSDs),":[72],"as":[73],"signals":[76],"RL":[80],"and":[81],"invariant":[82],"distractions.":[85,147],"Specifically,":[86],"effectively":[88],"capture":[89],"via":[93],"RSDs,":[94],"CRESP":[95,127],"introduces":[96],"an":[97],"auxiliary":[98],"task---that":[99],"is,":[100],"predicting":[101],"characteristic":[103,122],"functions":[104],"RSDs---to":[106],"learn":[107],"representations,":[109],"because":[110],"well":[113],"approximate":[114],"leveraging":[119],"corresponding":[121],"functions.":[123],"Experiments":[124],"demonstrate":[125],"that":[126],"significantly":[128],"improves":[129],"generalization":[133],"on":[134,140],"unseen":[135],"environments,":[136],"outperforming":[137],"several":[138],"state-of-the-arts":[139],"DeepMind":[141],"Control":[142]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}