{"id":"https://openalex.org/W2964064620","doi":"https://doi.org/10.24963/ijcai.2018/420","title":"Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning","display_name":"Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2964064620","doi":"https://doi.org/10.24963/ijcai.2018/420","mag":"2964064620"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/420","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/420","pdf_url":"https://www.ijcai.org/proceedings/2018/0420.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0420.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026660809","display_name":"Haiyan Yin","orcid":"https://orcid.org/0009-0007-9576-9398"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haiyan Yin","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069034952","display_name":"Jianda Chen","orcid":"https://orcid.org/0000-0001-8269-1463"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jianda Chen","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082984558","display_name":"Sinno Jialin Pan","orcid":"https://orcid.org/0000-0001-6565-3836"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sinno Jialin Pan","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.3395,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64182137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3026","last_page":"3032"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9923999905586243,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9125000238418579,"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":0.88204425573349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.740476667881012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7313510179519653},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5815430879592896},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5546268820762634},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5283679962158203},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5194563269615173},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5065957307815552},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5018842220306396},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47882774472236633},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4673854112625122},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45751187205314636},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44677355885505676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08892321586608887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.88204425573349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740476667881012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7313510179519653},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5815430879592896},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5546268820762634},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5283679962158203},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5194563269615173},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5065957307815552},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5018842220306396},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47882774472236633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4673854112625122},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45751187205314636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44677355885505676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08892321586608887},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/420","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/420","pdf_url":"https://www.ijcai.org/proceedings/2018/0420.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/420","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/420","pdf_url":"https://www.ijcai.org/proceedings/2018/0420.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5280407516","display_name":null,"funder_award_id":"Tier-1 grant","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G8771026661","display_name":null,"funder_award_id":"M4081532.020","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964064620.pdf","grobid_xml":"https://content.openalex.org/works/W2964064620.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1522301498","https://openalex.org/W1554233645","https://openalex.org/W1959608418","https://openalex.org/W1988526405","https://openalex.org/W2118688707","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2174786457","https://openalex.org/W2201581102","https://openalex.org/W2260756217","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2419612459","https://openalex.org/W2436711315","https://openalex.org/W2561776174","https://openalex.org/W2596982695","https://openalex.org/W2604618034","https://openalex.org/W2614839826","https://openalex.org/W2663108269","https://openalex.org/W2949475445","https://openalex.org/W2951799221","https://openalex.org/W2952509347","https://openalex.org/W2963276097","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4230940751","https://openalex.org/W4297791094","https://openalex.org/W4298174377","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W2381242807","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2262250234"],"abstract_inverted_index":{"In":[0,62,131,170],"deep":[1,50,73,109],"reinforcement":[2],"learning":[3],"(RL)":[4],"tasks,":[5,47],"an":[6,15,81],"efficient":[7],"exploration":[8,70],"mechanism":[9],"should":[10],"be":[11],"able":[12],"to":[13,17,22,84,112,125,133,142,195],"encourage":[14],"agent":[16,83,194],"take":[18],"actions":[19],"that":[20],"lead":[21],"less":[23],"frequent":[24,199],"states":[25,44],"which":[26],"may":[27],"yield":[28],"higher":[29],"accumulative":[30],"future":[31,38,88,97,114,158,184],"return.":[32],"However,":[33],"both":[34],"knowing":[35],"about":[36],"the":[37,41,78,87,92,95,128,135,139,144,147,152,156,166,180,183,193,197],"and":[39,90,120,160,190],"evaluating":[40,179],"frequentness":[42,93,145],"of":[43,154,182],"are":[45],"non-trivial":[46],"especially":[48],"for":[49,72,80,94,146,178],"RL":[51,82],"domains,":[52],"where":[53,75],"a":[54,67,100,108,117,121,175],"state":[55],"is":[56],"represented":[57],"by":[58,187],"high-dimensional":[59],"image":[60],"frames.":[61,130],"this":[63,104,171],"paper,":[64],"we":[65,76,106,150,173],"propose":[66],"novel":[68],"informed":[69],"framework":[71],"RL,":[74],"build":[77],"capability":[79],"predict":[85,113],"over":[86,127],"transitions":[89],"evaluate":[91,143],"predicted":[96,148,157],"frames":[98,115,141,159,164],"in":[99],"meaningful":[101],"manner.":[102],"To":[103],"end,":[105],"train":[107],"prediction":[110],"model":[111,124],"given":[116],"state-action":[118],"pair,":[119],"convolutional":[122],"autoencoder":[123],"hash":[126],"seen":[129,140,163],"addition,":[132],"utilize":[134],"counts":[136],"derived":[137],"from":[138],"frames,":[149],"tackle":[151],"challenge":[153],"matching":[155],"their":[161],"corresponding":[162],"at":[165],"latent":[167],"feature":[168],"level.":[169],"way,":[172],"derive":[174],"reliable":[176],"metric":[177],"novelty":[181],"direction":[185],"pointed":[186],"each":[188],"action,":[189],"hence":[191],"inform":[192],"explore":[196],"least":[198],"one.":[200]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}