{"id":"https://openalex.org/W2144020421","doi":"https://doi.org/10.1109/robot.2009.5152289","title":"Least absolute policy iteration for robust value function approximation","display_name":"Least absolute policy iteration for robust value function approximation","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2144020421","doi":"https://doi.org/10.1109/robot.2009.5152289","mag":"2144020421"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2009.5152289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2009.5152289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},"type":"article","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/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073076975","display_name":"Hirotaka Hachiya","orcid":"https://orcid.org/0000-0003-3748-4101"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirotaka Hachiya","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102905217","display_name":"Hisashi Kashima","orcid":"https://orcid.org/0000-0002-5906-7571"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Hisashi Kashima","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, Japan","IBM Research, Tokyo Research Laboratory, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089173802","display_name":"Tetsuro Morimura","orcid":"https://orcid.org/0009-0002-9711-8023"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Tetsuro Morimura","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, Japan","IBM Research, Tokyo Research Laboratory, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072744508"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":1.3515,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85561643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"4","issue":null,"first_page":"2904","last_page":"2909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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":0.9959999918937683,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9916999936103821,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9900000095367432,"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/robustness","display_name":"Robustness (evolution)","score":0.8821648359298706},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7140095233917236},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.704757571220398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465755105018616},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.594761848449707},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.5138900279998779},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.468898206949234},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.45787307620048523},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.41654422879219055},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3960148096084595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3860681653022766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35360515117645264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23696565628051758}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8821648359298706},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7140095233917236},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.704757571220398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465755105018616},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.594761848449707},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5138900279998779},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.468898206949234},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45787307620048523},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.41654422879219055},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3960148096084595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3860681653022766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35360515117645264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23696565628051758},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robot.2009.5152289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2009.5152289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.5752","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.5752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sugiyama-www.cs.titech.ac.jp/~sugi/2009/ICRA2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1514587017","https://openalex.org/W1515851193","https://openalex.org/W1576452626","https://openalex.org/W1578080815","https://openalex.org/W1585575029","https://openalex.org/W1600046456","https://openalex.org/W2002748013","https://openalex.org/W2099767582","https://openalex.org/W2105078254","https://openalex.org/W2121863487","https://openalex.org/W2129249398","https://openalex.org/W2169106666","https://openalex.org/W2296319761","https://openalex.org/W2489822048","https://openalex.org/W2498631646","https://openalex.org/W2566307933","https://openalex.org/W2586680856","https://openalex.org/W3124407081","https://openalex.org/W4214717370","https://openalex.org/W4236670843","https://openalex.org/W4250589301","https://openalex.org/W4285719527","https://openalex.org/W6630907848","https://openalex.org/W6635798015"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W2965004901","https://openalex.org/W2921905705","https://openalex.org/W4233178034","https://openalex.org/W2003293420"],"abstract_inverted_index":{"Least-squares":[0],"policy":[1],"iteration":[2],"is":[3,48,68],"a":[4,51],"useful":[5],"reinforcement":[6],"learning":[7],"method":[8,34,47],"in":[9,24],"robotics":[10],"due":[11],"to":[12,19,22],"its":[13],"computational":[14,66],"efficiency.":[15],"However,":[16],"it":[17],"tends":[18],"be":[20,57],"sensitive":[21],"outliers":[23],"observed":[25],"rewards.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"propose":[31],"an":[32],"alternative":[33],"that":[35],"employs":[36],"the":[37,65,78,81],"absolute":[38],"loss":[39],"for":[40,71],"enhancing":[41],"robustness":[42,73],"and":[43,74],"reliability.":[44,75],"The":[45],"proposed":[46,82],"formulated":[49],"as":[50],"linear":[52],"programming":[53],"problem":[54],"which":[55],"can":[56],"solved":[58],"efficiently":[59],"by":[60],"standard":[61],"optimization":[62],"software,":[63],"so":[64],"advantage":[67],"not":[69],"sacrificed":[70],"gaining":[72],"We":[76],"demonstrate":[77],"usefulness":[79],"of":[80],"approach":[83],"through":[84],"simulated":[85],"robot-control":[86],"tasks.":[87]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}