{"id":"https://openalex.org/W3204145130","doi":"https://doi.org/10.1145/3517207.3526968","title":"Temporal shift reinforcement learning","display_name":"Temporal shift reinforcement learning","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W3204145130","doi":"https://doi.org/10.1145/3517207.3526968","mag":"3204145130"},"language":"en","primary_location":{"id":"doi:10.1145/3517207.3526968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517207.3526968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.02145","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007430044","display_name":"Deepak George Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Deepak George Thomas","raw_affiliation_strings":["Department of Computer Science","Iowa State University\u2028"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Iowa State University\u2028","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017176660","display_name":"Tichakorn Wongpiromsarn","orcid":"https://orcid.org/0000-0002-3977-122X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tichakorn Wongpiromsarn","raw_affiliation_strings":["Department of Computer Science","Iowa State University\u2028"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Iowa State University\u2028","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079359777","display_name":"Ali Jannesari","orcid":"https://orcid.org/0000-0001-8672-5317"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jannesari","raw_affiliation_strings":["Department of Computer Science","Iowa State University\u2028"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Iowa State University\u2028","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007430044"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00581602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"100"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9962999820709229,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8779138326644897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7306100130081177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.634485125541687},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5976274013519287},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.544894814491272},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5279105305671692},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.507108211517334},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5026955604553223},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4220700263977051},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41963380575180054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35109788179397583}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8779138326644897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7306100130081177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.634485125541687},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5976274013519287},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.544894814491272},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5279105305671692},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.507108211517334},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5026955604553223},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4220700263977051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41963380575180054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35109788179397583},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3517207.3526968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517207.3526968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.02145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.02145","pdf_url":"https://arxiv.org/pdf/2109.02145","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3204145130","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.02145.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2109.02145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.02145","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.02145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.02145","pdf_url":"https://arxiv.org/pdf/2109.02145","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204145130.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2016053056","https://openalex.org/W2115211925","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2156303437","https://openalex.org/W2507009361","https://openalex.org/W2529601334","https://openalex.org/W2745868649","https://openalex.org/W2746553466","https://openalex.org/W2770804203","https://openalex.org/W2799176631","https://openalex.org/W2963477884","https://openalex.org/W2963524571","https://openalex.org/W2963617068","https://openalex.org/W2968883249","https://openalex.org/W2990152177","https://openalex.org/W3011985620","https://openalex.org/W3021708257","https://openalex.org/W3103780890","https://openalex.org/W3115293622","https://openalex.org/W3119425543"],"related_works":["https://openalex.org/W3197115698","https://openalex.org/W2962779867","https://openalex.org/W3037179286","https://openalex.org/W3034359401","https://openalex.org/W2133040789","https://openalex.org/W2428834750","https://openalex.org/W3211941939","https://openalex.org/W2072164538","https://openalex.org/W2131021149","https://openalex.org/W2967645217","https://openalex.org/W2160308170","https://openalex.org/W2105486945","https://openalex.org/W3005346806","https://openalex.org/W2939075711","https://openalex.org/W3093470997","https://openalex.org/W3029221344","https://openalex.org/W3201768179","https://openalex.org/W2491675558","https://openalex.org/W2990183740","https://openalex.org/W2062122188"],"abstract_inverted_index":{"The":[0],"function":[1],"approximators":[2],"employed":[3],"by":[4],"traditional":[5],"image-based":[6],"Deep":[7],"Reinforcement":[8,32],"Learning":[9,33],"(DRL)":[10],"algorithms":[11],"usually":[12],"lack":[13],"a":[14,28],"temporal":[15,55],"learning":[16,22],"component":[17],"and":[18],"instead":[19],"focus":[20],"on":[21,68,76],"the":[23,62,71,79,90],"spatial":[24,41],"component.":[25],"We":[26,57],"propose":[27],"technique,":[29],"Temporal":[30],"Shift":[31],"(TSRL),":[34],"wherein":[35],"both":[36,69],"temporal,":[37],"as":[38,40,92,94],"well":[39,93],"components":[42],"are":[43],"jointly":[44],"learned.":[45],"Moreover,":[46],"TSRL":[47,60],"does":[48],"not":[49],"require":[50],"additional":[51],"parameters":[52],"to":[53],"perform":[54],"learning.":[56],"show":[58],"that":[59],"outperforms":[61],"commonly":[63],"used":[64],"frame":[65],"stacking":[66],"heuristic":[67],"of":[70,83],"Atari":[72],"environments":[73],"we":[74],"test":[75],"while":[77],"beating":[78],"SOTA":[80],"for":[81],"one":[82],"them.":[84],"This":[85],"investigation":[86],"has":[87],"implications":[88],"in":[89],"robotics":[91],"sequential":[95],"decision-making":[96],"domains.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}