{"id":"https://openalex.org/W3133427729","doi":"https://doi.org/10.1007/978-3-030-69322-0_9","title":"Policy Advisory Module for Exploration Hindrance Problem in Multi-agent Deep Reinforcement Learning","display_name":"Policy Advisory Module for Exploration Hindrance Problem in Multi-agent Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3133427729","doi":"https://doi.org/10.1007/978-3-030-69322-0_9","mag":"3133427729"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-69322-0_9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-69322-0_9","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5101460829","display_name":"Jiahao Peng","orcid":"https://orcid.org/0000-0002-9011-1040"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jiahao Peng","raw_affiliation_strings":["Computer Science and Engineering, Waseda University, Tokyo, 1698555, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Waseda University, Tokyo, 1698555, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082205147","display_name":"Toshiharu Sugawara","orcid":"https://orcid.org/0000-0002-9271-4507"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiharu Sugawara","raw_affiliation_strings":["Computer Science and Engineering, Waseda University, Tokyo, 1698555, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9271-4507","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Waseda University, Tokyo, 1698555, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101460829"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02233008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8387695550918579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642200589179993},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5757371187210083},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4995396137237549},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48884886503219604},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46608966588974},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.45586538314819336},{"id":"https://openalex.org/keywords/search-and-rescue","display_name":"Search and rescue","score":0.4278203845024109},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4259305000305176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42529192566871643},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.3563650846481323},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3510933518409729},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.34632042050361633},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.34494537115097046},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09949538111686707},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07094612717628479}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8387695550918579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642200589179993},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5757371187210083},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4995396137237549},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48884886503219604},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46608966588974},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.45586538314819336},{"id":"https://openalex.org/C2775935494","wikidata":"https://www.wikidata.org/wiki/Q741964","display_name":"Search and rescue","level":3,"score":0.4278203845024109},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4259305000305176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42529192566871643},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3563650846481323},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3510933518409729},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.34632042050361633},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.34494537115097046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09949538111686707},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07094612717628479},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-69322-0_9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-69322-0_9","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G4757044010","display_name":"Improving sustainability, flexibility, and robustness of artifactitious systems using emergence of divisional cooperation","funder_award_id":"17KT0044","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1536258751","https://openalex.org/W1656616331","https://openalex.org/W2088956500","https://openalex.org/W2107112577","https://openalex.org/W2594794854","https://openalex.org/W2754517384","https://openalex.org/W2766578459","https://openalex.org/W2897890437","https://openalex.org/W2963407617","https://openalex.org/W2981366899","https://openalex.org/W4245478579","https://openalex.org/W6610313133","https://openalex.org/W6630100470"],"related_works":["https://openalex.org/W4317634134","https://openalex.org/W2889566344","https://openalex.org/W2981729160","https://openalex.org/W4206733587","https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W3005999311","https://openalex.org/W3042530408","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}