{"id":"https://openalex.org/W7057071739","doi":null,"title":"Ghost In the Grid: Challenges for Reinforcement Learning in Grid World Environments","display_name":"Ghost In the Grid: Challenges for Reinforcement Learning in Grid World Environments","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7057071739"},"language":"en","primary_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/89875","doi":null,"is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/89875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5012897368","display_name":"Chris Bamford","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bamford, C","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5012897368"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24727157,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0006000000284984708,"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/T10906","display_name":"AI-based Problem Solving and Planning","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/grid-world","display_name":"grid world","score":0.7059999704360962},{"id":"https://openalex.org/keywords/procedural-environment-generation","display_name":"procedural environment generation","score":0.6069999933242798},{"id":"https://openalex.org/keywords/geometric-deep-learning","display_name":"geometric deep learning","score":0.9470000267028809},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.800000011920929},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.5180000066757202}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8844000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684000134468079},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5584999918937683},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.413100004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4052000045776367},{"id":"https://openalex.org/C2780565519","wikidata":"https://www.wikidata.org/wiki/Q1208937","display_name":"Multitude","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2393999993801117},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.23579999804496765},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2320999950170517},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.22660000622272491},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.22550000250339508},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.2248000055551529},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2198999971151352},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.20520000159740448},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.19370000064373016},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.19030000269412994},{"id":"https://openalex.org/C170828538","wikidata":"https://www.wikidata.org/wiki/Q1751513","display_name":"Game mechanics","level":2,"score":0.1868000030517578},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.18449999392032623},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.1826000064611435},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18250000476837158},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.17980000376701355},{"id":"https://openalex.org/C503285160","wikidata":"https://www.wikidata.org/wiki/Q858057","display_name":"Game design","level":2,"score":0.17800000309944153}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/89875","doi":null,"is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/89875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133202780","https://openalex.org/W3103223352","https://openalex.org/W6903697112","https://openalex.org/W7086628567","https://openalex.org/W4415797730","https://openalex.org/W2889267552","https://openalex.org/W4283270478","https://openalex.org/W7213886328","https://openalex.org/W7212603487","https://openalex.org/W3037871539"],"abstract_inverted_index":{"The":[0,258],"current":[1],"state-of-the-art":[2,85],"deep":[3,255,369],"reinforcement":[4,108,157],"learning":[5,158,175,250],"techniques":[6],"require":[7],"agents":[8],"to":[9,16,32,61,133,195,307,346,351,382,393],"gather":[10],"large":[11],"amounts":[12],"of":[13,56,70,87,165,173,181,187,234,271,319,336,366,399],"diverse":[14],"experiences":[15],"train":[17],"effective":[18],"and":[19,52,90,100,137,152,204,274,403],"general":[20],"models.":[21],"In":[22,64,193],"addition,":[23],"there":[24],"are":[25,123,238,287,311],"also":[26],"many":[27,227],"other":[28],"factors":[29,318],"that":[30,58,82,94,120,167,208,218,237,310,326,373,405],"have":[31],"be":[33,131,210],"taken":[34],"into":[35],"consideration:":[36],"for":[37,103,150,156,293],"example,":[38],"how":[39],"the":[40,54,179,242,317,320,332,344,356,364,383,397,409],"agent":[41],"interacts":[42],"with":[43,125,145],"its":[44],"environment;":[45],"parameter":[46],"optimization":[47],"techniques;":[48],"environment":[49],"exploration":[50],"methods;":[51],"finally":[53],"diversity":[55],"environments":[57,155,348],"is":[59,263,324],"provided":[60],"an":[62],"agent.":[63],"this":[65,219],"thesis,":[66],"we":[67,74,183,200,248,354],"investigate":[68],"several":[69,232,387],"these":[71,196,327,394,406],"factors.":[72],"Firstly":[73],"introduce":[75],"Griddly,":[76],"a":[77,84,98,147,162,171,185,205,213,291],"high-performance":[78],"grid-world":[79,154,251],"game":[80,252,261],"engine":[81],"provides":[83,161],"combination":[86],"high":[88],"performance":[89,268],"flexibility.":[91],"We":[92,118,141,216,229,371,390],"demonstrate":[93,404],"grid":[95],"worlds":[96],"provide":[97,201,391],"principled":[99],"expressive":[101],"substrate":[102],"fundamental":[104],"research":[105,224,236],"questions":[106],"in":[107,115,170,212,226,269,359,386,396],"learning,":[109],"whilst":[110],"filtering":[111],"out":[112],"noise":[113],"inherent":[114,357],"physical":[116],"systems.":[117],"show":[119,217,372],"although":[121],"grid-worlds":[122],"constructed":[124],"simple":[126],"rules-based":[127],"mechanics,":[128],"they":[129],"can":[130,209],"used":[132],"construct":[134],"complex":[135,189,197,296,347],"open-ended,":[136],"procedurally":[138],"generated":[139],"environments.":[140],"improve":[142],"upon":[143],"Griddly":[144],"GriddlyJS,":[146],"web-based":[148],"tool":[149],"designing":[151],"testing":[153],"research.":[159],"GriddlyJS":[160,182],"rich":[163],"suite":[164],"features":[166,180,243],"assist":[168],"researchers":[169],"multitude":[172],"different":[174],"approaches.":[176],"To":[177],"highlight":[178],"present":[184],"dataset":[186],"100":[188],"escape-room":[190],"puzzle":[191,198],"levels.":[192],"addition":[194],"levels,":[199],"human-generated":[202],"trajectories":[203],"baseline":[206],"policy":[207],"run":[211],"web":[214],"browser.":[215],"tooling":[220],"enables":[221],"significantly":[222,349],"faster":[223],"iteration":[225],"sub-fields.":[228],"then":[230],"explore":[231,249,355],"areas":[233],"RL":[235],"made":[239],"accessible":[240],"by":[241,245],"introduced":[244,264,288],"Griddly:":[246],"Firstly,":[247],"mechanics":[253],"using":[254,363],"neural":[256,260,337],"networks.":[257],"{\\\\em":[259,283,367],"engine}":[262],"which":[265,289],"has":[266],"competitive":[267],"terms":[270],"sample":[272],"efficiency":[273],"predicting":[275],"states":[276],"accurately":[277],"over":[278,316],"long":[279],"time":[280],"horizons.":[281],"Secondly,":[282],"conditional":[284],"action":[285,298,302,308,321,329],"trees}":[286],"describe":[290],"method":[292],"compactly":[294],"expressing":[295],"hierarchical":[297,301],"spaces.":[299],"Expressing":[300],"spaces":[303,309,330],"as":[304],"trees":[305],"leads":[306],"additive":[312],"rather":[313],"than":[314],"multiplicative":[315],"space.":[322],"It":[323],"shown":[325],"compressed":[328],"reduce":[331],"required":[333],"output":[334],"size":[335],"networks":[338],"without":[339],"compromising":[340],"performance.":[341],"This":[342],"makes":[343],"interfaces":[345],"simpler":[350],"implement.":[352],"Finally,":[353],"symmetry":[358],"common":[360],"observation":[361],"spaces,":[362],"concept":[365],"geometric":[368,375],"learning}.":[370],"certain":[374],"data":[376],"augmentation":[377],"methods":[378,407],"do":[379],"not":[380],"conform":[381],"underlying":[384,410],"assumptions":[385],"training":[388],"algorithms.":[389],"solutions":[392],"problems":[395],"form":[398],"novel":[400],"regularization":[401],"functions":[402],"fix":[408],"assumptions.":[411]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}