{"id":"https://openalex.org/W2240299599","doi":"https://doi.org/10.21236/ada624278","title":"Enhanced Experience Replay for Deep Reinforcement Learning","display_name":"Enhanced Experience Replay for Deep Reinforcement Learning","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2240299599","doi":"https://doi.org/10.21236/ada624278","mag":"2240299599"},"language":"en","primary_location":{"id":"doi:10.21236/ada624278","doi":"https://doi.org/10.21236/ada624278","is_oa":false,"landing_page_url":"http://doi.org/10.21236/ada624278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"U.S. Army Research Lab Computational Info","raw_type":"report"},"volume":null,"type":"report","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/A5036592878","display_name":"David M. Doria","orcid":"https://orcid.org/0000-0002-6176-3576","observed_orcids":["https://orcid.org/0000-0002-6176-3576"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Doria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049251389","display_name":"Bryan P. Dawson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Dawson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076163601","display_name":"Manuel M. Vindiola","orcid":"https://orcid.org/0000-0003-4420-3312","observed_orcids":["https://orcid.org/0000-0003-4420-3312"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Vindiola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.00019999999494757503,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/experience-replay","display_name":"experience replay","score":0.953000009059906},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.972000002861023},{"id":"https://openalex.org/keywords/atari-2600","display_name":"Atari 2600","score":0.9269999861717224},{"id":"https://openalex.org/keywords/state-similarity","display_name":"state similarity","score":0.48500001430511475},{"id":"https://openalex.org/keywords/behavioral-consistency","display_name":"behavioral consistency","score":0.515999972820282},{"id":"https://openalex.org/keywords/video-game-control","display_name":"video game control","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7675819993019104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5497348308563232},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5009121894836426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3165912628173828},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23113271594047546},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05318412184715271}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21236/ada624278","doi":"https://doi.org/10.21236/ada624278","is_oa":false,"landing_page_url":"http://doi.org/10.21236/ada624278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"U.S. Army Research Lab Computational Info","raw_type":"report"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2481567506","https://openalex.org/W2201581102","https://openalex.org/W4410984665","https://openalex.org/W2970283989","https://openalex.org/W1757796397","https://openalex.org/W2980512966","https://openalex.org/W2588283865","https://openalex.org/W2556958149","https://openalex.org/W3213049467","https://openalex.org/W2625858940"],"abstract_inverted_index":{"Abstract":[0],":":[1],"Deep":[2],"reinforcement":[3,180],"learning":[4,14,181],"recently":[5,148],"has":[6],"performed":[7],"very":[8],"well":[9],"in":[10,67,89],"the":[11,39,42,46,55,82,92,108,127,159,162,166,179,184],"task":[12],"of":[13,41,60,84,91,110,147,161],"control":[15],"policies":[16],"for":[17],"Atari":[18,28],"2600":[19],"games.":[20],"Using":[21],"raw":[22],"frames":[23],"taken":[24],"directly":[25],"from":[26],"an":[27,68,85,111],"emulator,":[29],"these":[30,116,195],"systems":[31],"train":[32,54],"a":[33,58,99,135,145,153,172],"convolutional":[34],"neural":[35],"network":[36],"to":[37,53,71,144,170],"interpret":[38],"state":[40,131],"game":[43],"and":[44,57,65,151,174,197],"select":[45],"optimal":[47],"action.":[48],"Temporal-difference":[49],"Q-learning":[50],"is":[51,63],"used":[52,66],"network,":[56],"memory":[59],"state-action-reward":[61],"transitions":[62,132],"kept":[64],"experience-reply":[69],"algorithm":[70],"increase":[72],"training":[73],"efficiency.":[74],"Recent":[75],"work":[76],"reports":[77],"performance":[78],"at":[79],"or":[80],"above":[81],"level":[83],"expert":[86],"human":[87],"player":[88],"many":[90],"games;":[93],"however,":[94],"when":[95],"evaluating":[96],"behavior":[97],"on":[98,183],"more":[100],"qualitative":[101],"level,":[102],"there":[103],"are":[104,168,190],"major":[105],"inconsistencies":[106],"with":[107],"actions":[109],"intelligent":[112],"player.":[113],"To":[114],"improve":[115],"behavioral":[117],"characteristics,":[118],"we":[119,125,139,176],"introduce":[120],"3":[121],"new":[122],"techniques:":[123],"1)":[124],"bias":[126],"experience-replay-selection":[128],"step":[129],"toward":[130],"that":[133],"received":[134],"positive":[136],"reward;":[137],"2)":[138],"compare":[140],"newly":[141],"observed":[142,149],"states":[143,150,167],"set":[146],"take":[152],"random":[154],"action":[155,160],"rather":[156],"than":[157],"accept":[158],"current":[163],"policy":[164],"if":[165],"similar":[169],"within":[171],"threshold;":[173],"3)":[175],"only":[177],"perform":[178],"updates":[182],"topmost":[185],"linear":[186],"layers":[187],"as":[188],"experiences":[189],"generated.":[191],"This":[192],"report":[193],"details":[194],"techniques":[196],"preliminary":[198],"results.":[199]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2016-06-24T00:00:00"}