{"id":"https://openalex.org/W3136456184","doi":"https://doi.org/10.1109/tpami.2021.3069005","title":"State-Temporal Compression in Reinforcement Learning With the Reward-Restricted Geodesic Metric","display_name":"State-Temporal Compression in Reinforcement Learning With the Reward-Restricted Geodesic Metric","publication_year":2021,"publication_date":"2021-03-25","ids":{"openalex":"https://openalex.org/W3136456184","doi":"https://doi.org/10.1109/tpami.2021.3069005","mag":"3136456184","pmid":"https://pubmed.ncbi.nlm.nih.gov/33764874"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3069005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3069005","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5048321911","display_name":"Shangqi Guo","orcid":"https://orcid.org/0000-0003-3181-6881"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqi Guo","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China","Beijing Innovation Center for Future Chip, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3181-6881","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chip, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683124","display_name":"Qi Yan","orcid":"https://orcid.org/0000-0002-1633-2320"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yan","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China","Beijing Innovation Center for Future Chip, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1633-2320","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chip, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640055","display_name":"Xin Su","orcid":"https://orcid.org/0000-0002-5979-8702"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Su","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China","Beijing Innovation Center for Future Chip, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5979-8702","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chip, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004579631","display_name":"Xiaolin Hu","orcid":"https://orcid.org/0000-0002-4907-7354"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["Department of Computer Science and Technology, Institute for Artificial Intelligence, Beijing National Research Center for Information Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4907-7354","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for Artificial Intelligence, Beijing National Research Center for Information Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352754","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-4813-2494"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Beijing Innovation Center for Future Chip, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4813-2494","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chip, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6824,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74285525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"44","issue":"9","first_page":"5572","last_page":"5589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9887999892234802,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8741058111190796},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7176975607872009},{"id":"https://openalex.org/keywords/geodesic","display_name":"Geodesic","score":0.7150065898895264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7040441036224365},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5436069965362549},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5353966355323792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232794880867004},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.4652104675769806},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32605117559432983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3023965358734131},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18834742903709412},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.06134164333343506}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8741058111190796},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7176975607872009},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.7150065898895264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7040441036224365},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5436069965362549},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5353966355323792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232794880867004},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.4652104675769806},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32605117559432983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3023965358734131},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18834742903709412},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.06134164333343506},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3069005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3069005","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:33764874","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33764874","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G4160143202","display_name":"\u7c7b\u8111\u795e\u7ecf\u7f51\u7edc\u5efa\u6a21\u3001\u5b66\u4e60\u4e0e\u5e94\u7528","funder_award_id":"61836014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6645987955","display_name":null,"funder_award_id":"U19B2034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7861851748","display_name":"\u901a\u7528\u7c7b\u8111\u8ba1\u7b97\u67b6\u6784\u6a21\u578b\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8260862593","display_name":"\u57fa\u4e8e\u6982\u7387\u56fe\u6a21\u578b\u7684\u5927\u89c4\u6a21\u89c6\u89c9\u76ae\u5c42\u8109\u51b2\u795e\u7ecf\u7f51\u7edc\u8ba1\u7b97\u673a\u7406\u7814\u7a76","funder_award_id":"61671266","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W1433129784","https://openalex.org/W1504915502","https://openalex.org/W1505937442","https://openalex.org/W1509780496","https://openalex.org/W1522301498","https://openalex.org/W1564393562","https://openalex.org/W1996648614","https://openalex.org/W2032916024","https://openalex.org/W2056354534","https://openalex.org/W2067635342","https://openalex.org/W2071056361","https://openalex.org/W2071302132","https://openalex.org/W2097381042","https://openalex.org/W2109910161","https://openalex.org/W2119972318","https://openalex.org/W2121517924","https://openalex.org/W2123447947","https://openalex.org/W2138621090","https://openalex.org/W2145339207","https://openalex.org/W2160808139","https://openalex.org/W2413708175","https://openalex.org/W2523124567","https://openalex.org/W2765308067","https://openalex.org/W2787066086","https://openalex.org/W2889222431","https://openalex.org/W2926786214","https://openalex.org/W2963011537","https://openalex.org/W2963523627","https://openalex.org/W2963871073","https://openalex.org/W2964227312","https://openalex.org/W2997101648","https://openalex.org/W3027095131","https://openalex.org/W4214717370","https://openalex.org/W4289666799","https://openalex.org/W6603137543","https://openalex.org/W6604362843","https://openalex.org/W6605715689","https://openalex.org/W6631190155","https://openalex.org/W6633793312","https://openalex.org/W6635516443","https://openalex.org/W6637806891","https://openalex.org/W6638739688","https://openalex.org/W6638898712","https://openalex.org/W6674600207","https://openalex.org/W6675715384","https://openalex.org/W6678481081","https://openalex.org/W6683841269","https://openalex.org/W6688576433","https://openalex.org/W6703271639","https://openalex.org/W6712173889","https://openalex.org/W6715299084","https://openalex.org/W6718190810","https://openalex.org/W6719911377","https://openalex.org/W6730038592","https://openalex.org/W6734215269","https://openalex.org/W6734325300","https://openalex.org/W6738165965","https://openalex.org/W6745277162","https://openalex.org/W6748012927","https://openalex.org/W6748848655","https://openalex.org/W6752089545","https://openalex.org/W6752255449","https://openalex.org/W6752656891","https://openalex.org/W6754957883","https://openalex.org/W6755459604","https://openalex.org/W6764088478","https://openalex.org/W6780170931","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4244492201","https://openalex.org/W2165546027","https://openalex.org/W2112348346","https://openalex.org/W1992053816","https://openalex.org/W2380813680","https://openalex.org/W4297785055","https://openalex.org/W2405812711","https://openalex.org/W2370128788","https://openalex.org/W3008292135","https://openalex.org/W2511960118"],"abstract_inverted_index":{"It":[0],"is":[1,30,100],"difficult":[2],"to":[3,26,31,61,85,125],"solve":[4,126],"complex":[5,127],"tasks":[6],"that":[7,62,93],"involve":[8],"large":[9,34],"state":[10],"spaces":[11],"and":[12,23,49,135],"long-term":[13],"decision":[14],"processes":[15],"by":[16,81],"reinforcement":[17,121],"learning":[18,122],"(RL)":[19],"algorithms.":[20],"A":[21],"common":[22],"promising":[24],"method":[25,144],"address":[27],"this":[28,42,68,114],"challenge":[29],"compress":[32],"a":[33,38,72,82],"RL":[35,106,147],"problem":[36,58,107],"into":[37],"small":[39],"one.":[40],"Towards":[41],"goal,":[43],"the":[44,52,56,64,97,104,140],"compression":[45,88,94],"should":[46,59],"be":[47,79],"state-temporal":[48,87],"optimality-preserving":[50,102],"(i.e.,":[51],"optimal":[53],"policy":[54],"of":[55,63,142],"compressed":[57],"correspond":[60],"uncompressed":[65],"problem).":[66],"In":[67],"paper,":[69],"we":[70,116],"propose":[71],"reward-restricted":[73],"geodesic":[74],"(RRG)":[75],"metric,":[76],"which":[77],"can":[78],"learned":[80],"neural":[83],"network,":[84],"perform":[86],"in":[89,130],"RL.":[90],"We":[91],"prove":[92],"based":[95],"on":[96],"RRG":[98,119],"metric":[99],"approximately":[101],"for":[103],"raw":[105],"endowed":[108],"with":[109],"temporally":[110],"abstract":[111],"actions.":[112],"With":[113],"compression,":[115],"design":[117],"an":[118],"metric-based":[120],"(RRG-RL)":[123],"algorithm":[124],"tasks.":[128],"Experiments":[129],"both":[131],"discrete":[132],"(2D":[133],"Minecraft)":[134],"continuous":[136],"(Doom)":[137],"environments":[138],"demonstrated":[139],"superiority":[141],"our":[143],"over":[145],"existing":[146],"approaches.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}