{"id":"https://openalex.org/W2080362542","doi":"https://doi.org/10.1109/adprl.2011.5967361","title":"Improved neural fitted Q iteration applied to a novel computer gaming and learning benchmark","display_name":"Improved neural fitted Q iteration applied to a novel computer gaming and learning benchmark","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2080362542","doi":"https://doi.org/10.1109/adprl.2011.5967361","mag":"2080362542"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5016014514","display_name":"Thomas Gabel","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thomas Gabel","raw_affiliation_strings":["Machine Learning Laboratory, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany","Machine Learning Lab, Department of Computer Science, University of Freiburg, 79110, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Learning Laboratory, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Machine Learning Lab, Department of Computer Science, University of Freiburg, 79110, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061082005","display_name":"Christian Lutz","orcid":"https://orcid.org/0000-0001-8698-9902"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Lutz","raw_affiliation_strings":["Machine Learning Laboratory, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany","Machine Learning Lab, Department of Computer Science, University of Freiburg, 79110, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Learning Laboratory, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Machine Learning Lab, Department of Computer Science, University of Freiburg, 79110, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Riedmiller","raw_affiliation_strings":["Machine Learning Laboratory, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany","Machine Learning Lab, Department of Computer Science, University of Freiburg, 79110, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Learning Laboratory, Department of Computer Science, University of Freiburg, Freiburg im Breisgau, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Machine Learning Lab, Department of Computer Science, University of Freiburg, 79110, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016014514"],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":1.3207,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84380952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9973000288009644,"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":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8315362930297852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8059998750686646},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7754309773445129},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6202669739723206},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.603416383266449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919308066368103},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5798707008361816},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.48944345116615295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47824493050575256},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.43489038944244385},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43484070897102356},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42341238260269165}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8315362930297852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8059998750686646},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7754309773445129},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6202669739723206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.603416383266449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919308066368103},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5798707008361816},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.48944345116615295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47824493050575256},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.43489038944244385},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43484070897102356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42341238260269165},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/adprl.2011.5967361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.9846","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.9846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ml.informatik.uni-freiburg.de/_media/publications/glr11.pdf","raw_type":"text"},{"id":"pmh:oai:fhffm.bsz-bw.de:5468","is_oa":false,"landing_page_url":"https://fhffm.bsz-bw.de/frontdoor/index/index/docId/5468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400774","display_name":"Scientific Publication Server (Frankfurt University of Applied Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5237613","host_organization_name":"Frankfurt University of Applied Sciences","host_organization_lineage":["https://openalex.org/I5237613"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W166862392","https://openalex.org/W1550698229","https://openalex.org/W1605202242","https://openalex.org/W2010798644","https://openalex.org/W2033016725","https://openalex.org/W2041367235","https://openalex.org/W2099833070","https://openalex.org/W2101533993","https://openalex.org/W2116709463","https://openalex.org/W2120346334","https://openalex.org/W2126025075","https://openalex.org/W2127038482","https://openalex.org/W2127412976","https://openalex.org/W2143908786","https://openalex.org/W2144304287","https://openalex.org/W2156361796","https://openalex.org/W2185441746","https://openalex.org/W2911296969","https://openalex.org/W4245296547","https://openalex.org/W6675078014","https://openalex.org/W6675086535","https://openalex.org/W6677132494","https://openalex.org/W6677737365"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Neural":[0],"batch":[1,41,162],"reinforcement":[2,16],"learning":[3,17,26,52,73],"(RL)":[4],"algorithms":[5],"have":[6],"recently":[7],"shown":[8],"to":[9],"be":[10,108,156],"a":[11,24,36,39,62,129,147],"powerful":[12],"tool":[13],"for":[14,65,96],"model-free":[15],"problems.":[18],"In":[19,75],"this":[20,48,116,122,143,170],"paper,":[21],"we":[22,145,192],"present":[23],"novel":[25,189],"benchmark":[27,180,191],"from":[28],"the":[29,45,51,66,77,81,97,103,112,133,167,173,176,185,188],"realm":[30],"of":[31,38,47,80,84,99,105,115,118,169,175,187],"computer":[32],"games":[33],"and":[34,54,70],"apply":[35],"variant":[37],"neural":[40,94,161],"RL":[42,163],"algorithm":[43],"in":[44,172,184],"scope":[46],"benchmark.":[49],"Defining":[50],"problem":[53],"appropriately":[55],"adjusting":[56],"all":[57],"relevant":[58],"parameters":[59],"is":[60,87,124,140],"often":[61],"tedious":[63],"task":[64,134],"researcher":[67],"who":[68],"implements":[69],"investigates":[71],"some":[72],"approach.":[74],"RL,":[76],"suitable":[78],"choice":[79],"function":[82,101,119],"c":[83,106],"immediate":[85],"costs":[86],"crucial,":[88],"and,":[89,135],"when":[90,127],"utilizing":[91],"multi-layer":[92],"perceptron":[93],"networks":[95],"purpose":[98],"value":[100],"approximation,":[102],"definition":[104],"must":[107],"well":[109,182],"aligned":[110],"with":[111],"specific":[113],"characteristics":[114],"type":[117],"approximator.":[120],"Determining":[121],"alignment":[123],"especially":[125],"tricky,":[126],"no":[128],"priori":[130],"knowledge":[131],"about":[132,137],"hence,":[136],"optimal":[138],"policies":[139],"available.":[141],"To":[142],"end,":[144],"propose":[146],"simple,":[148],"but":[149],"effective":[150],"dynamic":[151],"scaling":[152],"heuristic":[153,171],"that":[154],"can":[155],"seamlessly":[157],"integrated":[158],"into":[159],"contemporary":[160],"algorithms.":[164],"We":[165],"evaluate":[166],"effectiveness":[168],"context":[174,186],"well-known":[177],"pole":[178],"swing-up":[179],"as":[181,183],"gaming":[190],"are":[193],"suggesting.":[194]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}