{"id":"https://openalex.org/W2901843362","doi":null,"title":"The Architecture of a Multilayer Perceptron for Actor-Critic Algorithm with Energy-based Policy","display_name":"The Architecture of a Multilayer Perceptron for Actor-Critic Algorithm with Energy-based Policy","publication_year":2015,"publication_date":"2015-10-19","ids":{"openalex":"https://openalex.org/W2901843362","mag":"2901843362"},"language":"en","primary_location":{"id":"mag:2901843362","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01138709","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01138709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024114769","display_name":"Naoto Yoshida","orcid":"https://orcid.org/0000-0002-9813-0668","observed_orcids":["https://orcid.org/0000-0002-9813-0668"]},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naoto Yoshida","raw_affiliation_strings":["Tohoku University [Sendai]"],"raw_orcid":"https://orcid.org/0000-0002-9813-0668","affiliations":[{"raw_affiliation_string":"Tohoku University [Sendai]","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5024114769"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10320","display_name":"Neural Networks and Applications","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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/energy-based-models","display_name":"energy-based models","score":0.6880000233650208},{"id":"https://openalex.org/keywords/actor-critic-algorithms","display_name":"actor-critic algorithms","score":0.8510000109672546},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.7900000214576721},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.7490000128746033}],"concepts":[{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6719817519187927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914003849029541},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4852878749370575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4727771282196045},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.46078503131866455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.381082147359848},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23829221725463867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16354727745056152},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.12368753552436829},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06269684433937073},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.058837562799453735}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2901843362","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01138709","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:HAL:hal-01138709v2","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01138709","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2015","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"mag:2901843362","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01138709","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W104912628","https://openalex.org/W189596042","https://openalex.org/W1551329771","https://openalex.org/W1813659000","https://openalex.org/W2046376809","https://openalex.org/W2094387729","https://openalex.org/W2101539915","https://openalex.org/W2112796928","https://openalex.org/W2116064496","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2145805610","https://openalex.org/W2155027007","https://openalex.org/W2164858444","https://openalex.org/W2165225968","https://openalex.org/W2165235114","https://openalex.org/W2182304831"],"related_works":["https://openalex.org/W2182304831","https://openalex.org/W2594103415","https://openalex.org/W4297792361","https://openalex.org/W2612795874","https://openalex.org/W6941477018","https://openalex.org/W7133235368","https://openalex.org/W4386721514","https://openalex.org/W2165150801","https://openalex.org/W2510585945","https://openalex.org/W7099772943"],"abstract_inverted_index":{"Learning":[0],"and":[1,123],"acting":[2],"in":[3,15,40,179],"a":[4,153],"high":[5],"dimensional":[6],"state-action":[7],"space":[8],"are":[9],"one":[10],"of":[11,24,101,110,140,147,159,176],"the":[12,16,45,63,75,92,99,102,108,111,117,120,124,131,138,141,157,160,174],"central":[13],"problems":[14],"reinforcement":[17,26],"learning":[18,27,146],"(RL)":[19],"communities.":[20],"The":[21],"recent":[22],"development":[23],"model-free":[25],"algorithms":[28,47,56,72,128],"based":[29,73],"on":[30,74],"an":[31,89,148],"energy-based":[32,76,121],"model":[33],"have":[34],"been":[35],"shown":[36],"to":[37,107],"be":[38],"effective":[39],"such":[41],"domains.":[42,182],"However,":[43],"since":[44],"previous":[46],"used":[48],"neural":[49,82],"networks":[50,83],"with":[51,84],"stochastic":[52],"hidden":[53,86,94],"units,":[54,95],"these":[55],"required":[57],"Monte":[58],"Carlo":[59],"sampling":[60],"methods":[61],"for":[62],"action":[64],"selections.":[65],"In":[66],"this":[67,177],"paper,":[68],"we":[69,79,96,115,151,171],"investigate":[70],"actor-critic":[71],"model.":[77],"And":[78],"especially":[80],"use":[81,152],"deterministic":[85,93],"units":[87],"as":[88,156],"actor.":[90],"Introducing":[91],"show":[97,116,173],"that":[98,137],"gradient":[100,109,127],"objective":[103],"function":[104],"is":[105],"proportional":[106],"energy":[112,133],"function.":[113,134],"Then,":[114],"relationships":[118],"between":[119],"approach":[122],"conventional":[125],"policy":[126],"by":[129],"introducing":[130],"specific":[132],"We":[135,162],"reveal":[136],"specificity":[139],"RL":[142],"paradigm":[143],"severely":[144],"disturbs":[145],"actor":[149],"when":[150],"multilayer":[154],"perceptron":[155],"representation":[158],"policy.":[161],"therefore":[163],"introduce":[164],"\"":[165,168],"twin":[166],"net":[167],"architecture.":[169],"Finally,":[170],"empirically":[172],"effectiveness":[175],"architecture":[178],"several":[180],"discrete":[181]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2018-11-29T00:00:00"}