{"id":"https://openalex.org/W7124138453","doi":"https://doi.org/10.65109/ifut9064","title":"Investigating Practical Linear Temporal Difference Learning","display_name":"Investigating Practical Linear Temporal Difference Learning","publication_year":2016,"publication_date":"2016-05-09","ids":{"openalex":"https://openalex.org/W7124138453","doi":"https://doi.org/10.65109/ifut9064"},"language":"en","primary_location":{"id":"doi:10.65109/ifut9064","doi":"https://doi.org/10.65109/ifut9064","is_oa":false,"landing_page_url":"https://doi.org/10.65109/ifut9064","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1602.08771","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108277326","display_name":"Adam Adam","orcid":"https://orcid.org/0009-0006-6427-0554","observed_orcids":["https://orcid.org/0009-0006-6427-0554"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Adam","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101613484","display_name":"Martha White","orcid":"https://orcid.org/0000-0002-5356-2950","observed_orcids":["https://orcid.org/0000-0002-5356-2950"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martha White","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4585,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85796113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"494","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/off-policy-learning","display_name":"off-policy learning","score":0.781000018119812},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.9459999799728394},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.652999997138977},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.7289999723434448},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.9093999862670898},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7063000202178955},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.642300009727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182000041007996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.545799970626831},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2572000026702881}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.65109/ifut9064","doi":"https://doi.org/10.65109/ifut9064","is_oa":false,"landing_page_url":"https://doi.org/10.65109/ifut9064","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1602.08771","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.08771","pdf_url":"https://arxiv.org/pdf/1602.08771","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.1602.08771","doi":"https://doi.org/10.48550/arxiv.1602.08771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1602.08771","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1602.08771","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.08771","pdf_url":"https://arxiv.org/pdf/1602.08771","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124138453.pdf","grobid_xml":"https://content.openalex.org/works/W7124138453.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W75509695","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W1904705466","https://openalex.org/W1986014385","https://openalex.org/W2100677568","https://openalex.org/W2121863487","https://openalex.org/W2132622533","https://openalex.org/W2145339207","https://openalex.org/W2198988526","https://openalex.org/W2898016531","https://openalex.org/W2898155524"],"related_works":["https://openalex.org/W359568995","https://openalex.org/W2165905123","https://openalex.org/W7097492100","https://openalex.org/W1600046456","https://openalex.org/W7008801889","https://openalex.org/W2406456910","https://openalex.org/W2121703796","https://openalex.org/W7097390716","https://openalex.org/W7097873004","https://openalex.org/W2473364827"],"abstract_inverted_index":{"Off-policy":[0],"reinforcement":[1,38],"learning":[2,7,10],"has":[3,23],"many":[4],"applications":[5],"including:":[6],"from":[8],"demonstration,":[9],"multiple":[11],"goal":[12],"seeking":[13],"policies":[14],"in":[15,37,73,96],"parallel,":[16],"and":[17,49,99],"representing":[18],"predictive":[19],"knowledge.":[20],"Recently":[21],"there":[22],"been":[24],"an":[25,81],"proliferation":[26],"of":[27,76,87],"new":[28,64,89],"policy-evaluation":[29,67],"algorithms":[30],"that":[31],"fill":[32,70],"a":[33,71],"longstanding":[34],"algorithmic":[35],"void":[36],"learning:":[39],"combining":[40],"robustness":[41],"to":[42,84],"off-policy":[43],"sampling,":[44],"function":[45],"approximation,":[46],"linear":[47,90],"complexity,":[48],"temporal":[50],"difference":[51],"(TD)":[52],"updates.":[53],"This":[54],"paper":[55],"contains":[56],"two":[57,63],"main":[58],"contributions.":[59],"First,":[60],"we":[61,79],"derive":[62],"hybrid":[65],"TD":[66,91],"algorithms,":[68],"which":[69,86],"gap":[72],"this":[74],"collection":[75],"algorithms.":[77],"Second,":[78],"perform":[80],"empirical":[82],"comparison":[83],"elicit":[85],"these":[88],"methods":[92],"should":[93],"be":[94],"preferred":[95],"different":[97],"situations,":[98],"make":[100],"concrete":[101],"suggestions":[102],"about":[103],"practical":[104],"use.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-15T00:00:00"}