{"id":"https://openalex.org/W2893600742","doi":"https://doi.org/10.1109/ictai.2018.00015","title":"Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning","display_name":"Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2893600742","doi":"https://doi.org/10.1109/ictai.2018.00015","mag":"2893600742"},"language":"en","primary_location":{"id":"doi:10.1109/ictai.2018.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai.2018.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"type":"article","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/A5047790045","display_name":"Gino Brunner","orcid":"https://orcid.org/0000-0002-4341-2940"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gino Brunner","raw_affiliation_strings":["Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037533362","display_name":"Manuel Fritsche","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Manuel Fritsche","raw_affiliation_strings":["Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012797145","display_name":"Oliver Richter","orcid":"https://orcid.org/0000-0001-7886-5176"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Oliver Richter","raw_affiliation_strings":["Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078339613","display_name":"Roger Wattenhofer","orcid":"https://orcid.org/0000-0002-6339-3134"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roger Wattenhofer","raw_affiliation_strings":["Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology and Electrical Engineering, ETH Z\u00fcrich, Swizeland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.6759,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77975639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"1540","issue":null,"first_page":"25","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9829000234603882,"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/curiosity","display_name":"Curiosity","score":0.8997451066970825},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8092237114906311},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.701082706451416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6799051761627197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.607367992401123},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5503631234169006},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5257062315940857},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5132739543914795},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.487109899520874},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46571922302246094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43785661458969116},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2907021641731262},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1436564326286316},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09883219003677368},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09414035081863403}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8997451066970825},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8092237114906311},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.701082706451416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6799051761627197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607367992401123},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5503631234169006},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5257062315940857},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5132739543914795},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.487109899520874},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46571922302246094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43785661458969116},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2907021641731262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1436564326286316},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09883219003677368},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09414035081863403},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai.2018.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai.2018.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1522301498","https://openalex.org/W2034806191","https://openalex.org/W2514775068","https://openalex.org/W2596982695","https://openalex.org/W2603088459","https://openalex.org/W2950794298","https://openalex.org/W2950872548","https://openalex.org/W2963276097","https://openalex.org/W2963285578","https://openalex.org/W2963523627","https://openalex.org/W2963871073","https://openalex.org/W2963979925","https://openalex.org/W2964043796","https://openalex.org/W4297804636","https://openalex.org/W6607097208","https://openalex.org/W6631190155","https://openalex.org/W6685562342","https://openalex.org/W6692846177","https://openalex.org/W6717230150","https://openalex.org/W6726216181","https://openalex.org/W6729556111","https://openalex.org/W6735033012","https://openalex.org/W6735789912","https://openalex.org/W6735865323","https://openalex.org/W6748271565","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W1540839255"],"abstract_inverted_index":{"Learning":[0],"in":[1,8,67,90],"sparse":[2,113],"reward":[3],"settings":[4],"remains":[5],"a":[6,39,87,107],"challenge":[7],"Reinforcement":[9],"Learning,":[10],"which":[11,82],"is":[12,22,42,80,83,122],"often":[13],"addressed":[14],"by":[15,24],"using":[16],"intrinsic":[17],"rewards.":[18,114],"One":[19],"promising":[20],"strategy":[21],"inspired":[23],"human":[25],"curiosity,":[26],"requiring":[27],"the":[28,34,54,57,61,70,76,91,95,116,119,129],"agent":[29,41,55,121],"to":[30,32,44,124],"learn":[31,125],"predict":[33],"future.":[35],"In":[36,115],"this":[37,73],"paper":[38],"curiosity-driven":[40],"extended":[43,120],"use":[45],"these":[46],"predictions":[47],"directly":[48],"for":[49],"training.":[50],"To":[51],"achieve":[52],"this,":[53],"predicts":[56],"value":[58,78],"function":[59,79,93],"of":[60,72,94],"next":[62],"state":[63],"at":[64],"any":[65],"point":[66],"time.":[68],"Subsequently,":[69],"consistency":[71],"prediction":[74],"with":[75,112],"current":[77],"measured,":[81],"then":[84],"used":[85],"as":[86,103,105],"regularization":[88],"term":[89],"loss":[92],"algorithm.":[96],"Experiments":[97],"were":[98],"made":[99],"on":[100,106],"grid-world":[101],"environments":[102],"well":[104],"3D":[108],"navigation":[109],"task,":[110],"both":[111],"first":[117],"case":[118],"able":[123],"significantly":[126],"faster":[127],"than":[128],"baselines.":[130]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}