{"id":"https://openalex.org/W2368601330","doi":"https://doi.org/10.1145/2903220.2903254","title":"Autonomous navigation of an over-actuated marine platform using reinforcement learning","display_name":"Autonomous navigation of an over-actuated marine platform using reinforcement learning","publication_year":2016,"publication_date":"2016-05-11","ids":{"openalex":"https://openalex.org/W2368601330","doi":"https://doi.org/10.1145/2903220.2903254","mag":"2368601330"},"language":"en","primary_location":{"id":"doi:10.1145/2903220.2903254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2903220.2903254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073043939","display_name":"Konstantinos Tziortziotis","orcid":null},"institutions":[{"id":"https://openalex.org/I194019607","display_name":"University of Ioannina","ror":"https://ror.org/01qg3j183","country_code":"GR","type":"education","lineage":["https://openalex.org/I194019607"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Tziortziotis","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Ioannina, Ioannina, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Ioannina, Ioannina, Greece","institution_ids":["https://openalex.org/I194019607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079375197","display_name":"Nikolaos Tziortziotis","orcid":"https://orcid.org/0000-0002-2175-2610"},"institutions":[{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nikolaos Tziortziotis","raw_affiliation_strings":["Computer Science Laboratory (LIX), Ecole Polytechnique, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Laboratory (LIX), Ecole Polytechnique, Paris","institution_ids":["https://openalex.org/I4210139461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023982962","display_name":"Kostas Vlachos","orcid":"https://orcid.org/0000-0002-9716-7661"},"institutions":[{"id":"https://openalex.org/I194019607","display_name":"University of Ioannina","ror":"https://ror.org/01qg3j183","country_code":"GR","type":"education","lineage":["https://openalex.org/I194019607"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kostas Vlachos","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Ioannina, Ioannina, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Ioannina, Ioannina, Greece","institution_ids":["https://openalex.org/I194019607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051092577","display_name":"Konstantinos Blekas","orcid":"https://orcid.org/0000-0003-1085-8177"},"institutions":[{"id":"https://openalex.org/I194019607","display_name":"University of Ioannina","ror":"https://ror.org/01qg3j183","country_code":"GR","type":"education","lineage":["https://openalex.org/I194019607"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Blekas","raw_affiliation_strings":["Department of Computer Science & Engineering, University of Ioannina, Ioannina, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of Ioannina, Ioannina, Greece","institution_ids":["https://openalex.org/I194019607"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3883,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57643899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9336152076721191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6575519442558289},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5615341663360596},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5562225580215454},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5147445201873779},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4686659574508667},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4395182728767395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.384038507938385},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3228878378868103},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27033722400665283},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10896754264831543},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0830804705619812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9336152076721191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575519442558289},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5615341663360596},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5562225580215454},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5147445201873779},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4686659574508667},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4395182728767395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.384038507938385},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3228878378868103},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27033722400665283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10896754264831543},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0830804705619812},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2903220.2903254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2903220.2903254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Hellenic Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.75,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W46153032","https://openalex.org/W174941419","https://openalex.org/W602036032","https://openalex.org/W1515851193","https://openalex.org/W1540154259","https://openalex.org/W1582436621","https://openalex.org/W1590684588","https://openalex.org/W1972085072","https://openalex.org/W1976081037","https://openalex.org/W2021713368","https://openalex.org/W2084202551","https://openalex.org/W2105551637","https://openalex.org/W2106261932","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2147750403","https://openalex.org/W2150923691","https://openalex.org/W2156974606","https://openalex.org/W2291124468","https://openalex.org/W2502094132","https://openalex.org/W3100949653","https://openalex.org/W3209569680","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4230356358","https://openalex.org/W4236708315","https://openalex.org/W4240841252","https://openalex.org/W4285719527","https://openalex.org/W6601897666","https://openalex.org/W6634907821","https://openalex.org/W6635423901","https://openalex.org/W6677916085","https://openalex.org/W6682443896"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W2742483371","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W2025663273","https://openalex.org/W4399155503"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,9],"use":[4],"of":[5,11],"reinforcement":[6],"learning":[7],"for":[8,29],"navigation":[10,58],"an":[12,23],"over-actuated":[13],"marine":[14],"platform":[15,46],"in":[16,33,43],"unknown":[17,61],"environments.":[18],"The":[19,67],"proposed":[20],"approach":[21,42],"uses":[22],"online":[24],"least-squared":[25],"policy":[26],"iteration":[27],"scheme":[28],"value":[30],"function":[31],"approximation":[32],"order":[34],"to":[35,60],"estimate":[36],"optimal":[37,57],"policy.":[38],"We":[39],"evaluate":[40],"our":[41],"a":[44],"simulation":[45],"and":[47],"report":[48],"some":[49],"initial":[50],"results":[51,68],"concerning":[52],"its":[53],"performance":[54],"on":[55],"estimating":[56],"policies":[59],"environments":[62],"under":[63],"different":[64],"environmental":[65],"disturbances.":[66],"are":[69],"promising.":[70]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}