{"id":"https://openalex.org/W6907768873","doi":"https://doi.org/10.2312/stag.20241330","title":"Peek-a-bot: learning through vision in Unreal Engine","display_name":"Peek-a-bot: learning through vision in Unreal Engine","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6907768873","doi":"https://doi.org/10.2312/stag.20241330"},"language":"en","primary_location":{"id":"doi:10.2312/stag.20241330","is_oa":true,"landing_page_url":"https://doi.org/10.2312/stag.20241330","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2312/stag.20241330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pietra, Daniele Della","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pietra, Daniele Della","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Garau, Nicola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garau, Nicola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Conci, Nicola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Conci, Nicola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Granelli, Fabrizio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Granelli, Fabrizio","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37623185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7146000266075134,"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":0.7146000266075134,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07100000232458115,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.02850000001490116,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7257999777793884},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5257999897003174},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5127999782562256},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4851999878883362},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43389999866485596},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4219000041484833},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.40059998631477356},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3935000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051000237464905},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7257999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442000269889832},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027999937534332},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3781999945640564},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3257000148296356},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2615000009536743},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2312/stag.20241330","is_oa":true,"landing_page_url":"https://doi.org/10.2312/stag.20241330","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.2312/stag.20241330","is_oa":true,"landing_page_url":"https://doi.org/10.2312/stag.20241330","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"learn":[1,28],"to":[2,27,98,164,199],"navigate":[3],"and":[4,45,81,138,194,217],"interact":[5],"with":[6],"their":[7,10],"surroundings":[8],"through":[9,48],"senses,":[11],"particularly":[12],"vision.":[13],"Ego-vision":[14],"has":[15,51,65],"lately":[16],"become":[17],"a":[18,95,125,207],"significant":[19],"focus":[20],"in":[21,55],"computer":[22],"vision,":[23,109],"enabling":[24,196],"neural":[25],"networks":[26,50],"from":[29,70,157],"first-person":[30],"data":[31],"effectively,":[32],"as":[33,77],"we":[34,89],"humans":[35],"do.":[36],"Supervised":[37],"or":[38],"self-supervised":[39],"learning":[40,63,69,101],"of":[41,73,84,145,161,168,182,210],"depth,":[42],"object":[43],"location":[44],"segmentation":[46],"maps":[47],"deep":[49],"shown":[52],"considerable":[53],"success":[54],"recent":[56],"years.":[57],"On":[58],"the":[59,91,111,141,158,165,169,173,180,187,213],"other":[60,82],"hand,":[61],"reinforcement":[62,100],"(RL)":[64],"been":[66],"focusing":[67],"on":[68,108],"different":[71],"kinds":[72],"sensing":[74],"data,":[75],"such":[76],"rays,":[78],"collisions,":[79],"distances,":[80],"types":[83],"observations.":[85,116],"In":[86],"this":[87,185],"paper,":[88],"merge":[90],"two":[92],"approaches,":[93],"providing":[94],"complete":[96,215],"pipeline":[97],"train":[99,201],"agents":[102,204],"inside":[103,153],"virtual":[104],"environments,":[105],"only":[106],"relying":[107],"eliminating":[110],"need":[112],"for":[113],"traditional":[114],"RL":[115,203],"We":[117],"demonstrate":[118],"that":[119],"visual":[120,162],"stimuli,":[121],"if":[122],"encoded":[123],"by":[124],"carefully":[126],"designed":[127],"vision":[128],"encoder,":[129],"can":[130],"provide":[131],"informative":[132],"observations,":[133],"thus":[134],"replacing":[135],"ray-based":[136],"approaches":[137],"drastically":[139],"simplifying":[140],"reward":[142],"shaping":[143],"typical":[144],"classical":[146],"RL.":[147],"Our":[148],"method":[149],"is":[150,186],"fully":[151],"implemented":[152],"Unreal":[154],"Engine":[155],"5,":[156],"realtime":[159],"inference":[160],"features":[163],"online":[166],"training":[167],"agents'":[170],"behaviour":[171],"using":[172],"Proximal":[174],"Policy":[175],"Optimization":[176],"(PPO)":[177],"algorithm.":[178],"To":[179],"best":[181],"our":[183],"knowledge,":[184],"first":[188],"in-engine":[189],"solution":[190],"targeting":[191],"video":[192],"games":[193],"simulation,":[195],"game":[197],"developers":[198],"easily":[200],"vision-based":[202],"without":[205],"writing":[206],"single":[208],"line":[209],"code.":[211],"All":[212],"code,":[214],"experiments":[216],"analysis":[218],"will":[219],"be":[220],"available":[221],"at":[222],"https://mmlab-cv.github.io/Peek-a-bot/.":[223]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}