{"id":"https://openalex.org/W2771590356","doi":"https://doi.org/10.1109/humanoids.2017.8246959","title":"Deep reinforcement learning for conversational robots playing games","display_name":"Deep reinforcement learning for conversational robots playing games","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2771590356","doi":"https://doi.org/10.1109/humanoids.2017.8246959","mag":"2771590356"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2017.8246959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2017.8246959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Deep_reinforcement_learning_for_conversational_robots_playing_games/25173065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036357777","display_name":"Heriberto Cuay\u00e1huitl","orcid":"https://orcid.org/0000-0002-1937-9837"},"institutions":[{"id":"https://openalex.org/I51532219","display_name":"University of Lincoln","ror":"https://ror.org/03yeq9x20","country_code":"GB","type":"education","lineage":["https://openalex.org/I51532219"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Heriberto Cuayahuitl","raw_affiliation_strings":["University of Lincoln, Lincoln, Lincolnshire, GB"],"affiliations":[{"raw_affiliation_string":"University of Lincoln, Lincoln, Lincolnshire, GB","institution_ids":["https://openalex.org/I51532219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036357777"],"corresponding_institution_ids":["https://openalex.org/I51532219"],"apc_list":null,"apc_paid":null,"fwci":1.6628,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88491333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"abs 1504 702","issue":null,"first_page":"771","last_page":"776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9914000034332275,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8249863386154175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6941463947296143},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6225258708000183},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5142226219177246},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49061909317970276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43231919407844543},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13012158870697021},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05584287643432617}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8249863386154175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941463947296143},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6225258708000183},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5142226219177246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49061909317970276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43231919407844543},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13012158870697021},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05584287643432617}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/humanoids.2017.8246959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2017.8246959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:29060","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop contribution"},{"id":"pmh:oai:figshare.com:article/25173065","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Deep_reinforcement_learning_for_conversational_robots_playing_games/25173065","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/25173065","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Deep_reinforcement_learning_for_conversational_robots_playing_games/25173065","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W154472438","https://openalex.org/W1658008008","https://openalex.org/W1757796397","https://openalex.org/W1968962398","https://openalex.org/W2055048333","https://openalex.org/W2073384958","https://openalex.org/W2095436958","https://openalex.org/W2114199242","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2184188583","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2294065713","https://openalex.org/W2553109721","https://openalex.org/W2559112319","https://openalex.org/W2570651606","https://openalex.org/W2570972008","https://openalex.org/W2594693247","https://openalex.org/W2603550564","https://openalex.org/W2732273801","https://openalex.org/W2962948087","https://openalex.org/W2963262099","https://openalex.org/W2963477884","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2982543669","https://openalex.org/W3101008707","https://openalex.org/W4298857966","https://openalex.org/W4299401133","https://openalex.org/W6606244218","https://openalex.org/W6636881020","https://openalex.org/W6637967152","https://openalex.org/W6674534438","https://openalex.org/W6682849425","https://openalex.org/W6686207219","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6730013898"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Deep":[0,46],"reinforcement":[1],"learning":[2,20],"for":[3,9,55,116],"interactive":[4,118],"multimodal":[5],"robots":[6],"is":[7,33],"attractive":[8],"endowing":[10],"machines":[11],"with":[12,65,86],"trainable":[13],"skill":[14],"acquisition.":[15],"But":[16],"this":[17,31,41],"form":[18],"of":[19,82],"still":[21],"represents":[22],"several":[23],"challenges.":[24],"The":[25],"challenge":[26],"that":[27,53,97],"we":[28,43],"focus":[29],"in":[30,40,77],"paper":[32,42],"effective":[34,105],"policy":[35],"learning.":[36],"To":[37],"address":[38],"that,":[39],"compare":[44],"the":[45,59,66,80,108],"Q-Networks":[47],"(DQN)":[48],"method":[49,61,100],"against":[50],"a":[51],"variant":[52],"aims":[54],"stronger":[56],"decisions":[57,64],"than":[58,107],"original":[60],"by":[62],"avoiding":[63],"lowest":[67],"negative":[68],"rewards.":[69],"We":[70],"evaluated":[71],"our":[72,98],"baseline":[73,109],"and":[74,84,91],"proposed":[75,99],"algorithms":[76],"agents":[78],"playing":[79],"game":[81],"Noughts":[83],"Crosses":[85],"two":[87],"grid":[88],"sizes":[89],"(3\u00d73":[90],"5\u00d75).":[92],"Experimental":[93],"results":[94],"show":[95],"evidence":[96],"can":[101,113],"lead":[102],"to":[103],"more":[104],"policies":[106],"DQN":[110],"method,":[111],"which":[112],"be":[114],"used":[115],"training":[117],"social":[119],"robots.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}