{"id":"https://openalex.org/W6891831","doi":null,"title":"Agents in the Brickworld","display_name":"Agents in the Brickworld","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W6891831","mag":"6891831"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.508.8348","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.508.8348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/MAICS/2000/MAICS00-010.pdf","raw_type":"text"},"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/A5050310213","display_name":"Gregory D. Weber","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gregory D. Weber","raw_affiliation_strings":["\u2021Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Indiana University","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050310213"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":0.3986,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65846959,"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":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0010000000474974513,"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":0.0,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.5460000038146973},{"id":"https://openalex.org/keywords/causal-relationship","display_name":"causal relationship","score":0.5320000052452087},{"id":"https://openalex.org/keywords/relational-reinforcement-learning","display_name":"relational reinforcement learning","score":0.746999979019165},{"id":"https://openalex.org/keywords/multi-agent-environments","display_name":"multi-agent environments","score":0.5490000247955322},{"id":"https://openalex.org/keywords/stochastic-environments","display_name":"stochastic environments","score":0.746999979019165},{"id":"https://openalex.org/keywords/rule-based-agents","display_name":"rule-based agents","score":0.6539999842643738},{"id":"https://openalex.org/keywords/knowledge-representation","display_name":"knowledge representation","score":0.5329999923706055},{"id":"https://openalex.org/keywords/learning-to-plan","display_name":"learning to plan","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8251522183418274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6020846366882324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50413978099823},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.4841788113117218},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4655269980430603},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4268471598625183},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09470662474632263},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08725970983505249},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.08641061186790466},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.508.8348","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.508.8348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/MAICS/2000/MAICS00-010.pdf","raw_type":"text"},{"id":"mag:6891831","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/MAICS/2000/MAICS00-010.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1488730473","https://openalex.org/W1494114146","https://openalex.org/W1552549180","https://openalex.org/W1990182336","https://openalex.org/W2043441657","https://openalex.org/W2057774882","https://openalex.org/W2092919341","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2396715201","https://openalex.org/W3020831056"],"related_works":["https://openalex.org/W7097185653","https://openalex.org/W1592960552","https://openalex.org/W7171823761","https://openalex.org/W7098415485","https://openalex.org/W2149390907","https://openalex.org/W2396715201","https://openalex.org/W7221320708","https://openalex.org/W2989259882","https://openalex.org/W87178421","https://openalex.org/W2005540810"],"abstract_inverted_index":{"Brickworld":[0],"is":[1,27,71,105,187],"a":[2,10,54,60,74,82,133,163,172,220],"simulated":[3],"environment":[4,26,169],"which":[5,175,194],"has":[6,56,176],"been":[7,57],"developed":[8],"as":[9,59,126],"testbed":[11],"for":[12,17,167],"learning":[13,18,62,77,154,217],"and":[14,19,52,94,121,128,150,181,218],"planning--in":[15],"particular,":[16],"using":[20],"knowledge":[21,165],"of":[22,67,85,96,135,192,209,215],"causal":[23,83,92],"relations.":[24],"The":[25,49,64,101,159,202],"both":[28,89],"dynamic--there":[29],"are":[30],"other":[31,98],"\"agents":[32,103],"\"":[33,38,100,104],"whose":[34],"actions":[35],"affect":[36],"\"the":[37],"agent\u2019s":[39],"performance--and":[40],"stochastic---future":[41],"states":[42],"can":[43,131],"be":[44,132,196],"pre-dicted":[45],"only":[46,115],"with":[47],"uncertainty.":[48],"task,":[50],"building":[51],"maintaining":[53],"wall,":[55],"formulated":[58],"reinforce-ment":[61],"problem.":[63],"ultimate":[65],"goal":[66],"the":[68,86,97,109,168,207,213],"Brick-world":[69],"project":[70],"to":[72,190],"develop":[73],"relational":[75],"reinforcement":[76,153,216],"agent":[78],"that":[79,130,162],"will":[80],"learn":[81],"model":[84],"en-vironment":[87],"representing":[88],"its":[90],"own":[91],"powers":[93],"those":[95],"\"agents.":[99],"term":[102],"used":[106],"here":[107],"in":[108,171,212],"broadest":[110],"possible":[111],"sense,":[112],"including":[113],"not":[114],"intelligent":[116],"agents":[117],"but":[118],"brute":[119],"animals":[120],"even":[122],"natural":[123],"forces":[124],"such":[125],"wind":[127],"rain--anything":[129],"cause":[134],"environmental":[136],"change.":[137],"This":[138],"paper":[139,203],"describes":[140],"seven":[141],"implemented":[142],"agents--a":[143],"quasi-reactive":[144],"agent,":[145],"four":[146],"non-learning":[147],"rule-based":[148],"agents,":[149],"two":[151],"(non-relational)":[152],"agents--and":[155],"compares":[156],"their":[157],"performance.":[158],"experi-ments":[160],"show":[161],"reasonable":[164],"representation":[166],"results":[170],"state-value":[173],"function":[174],"local":[177],"optima,":[178],"making":[179],"greedy":[180],"e-greedy":[182],"policies":[183],"inappropriate.":[184],"Deeper":[185],"search":[186],"required,":[188],"lead-ing":[189],"problems":[191],"inefficiency,":[193],"may":[195],"allevi-ated":[197],"through":[198],"hierarchical":[199],"problem":[200],"spaces.":[201],"raises":[204],"questions":[205],"about":[206],"legitimacy":[208],"programmer-designed":[210],"hierarchies":[211],"framework":[214],"suggests":[219],"principled":[221],"solution.":[222]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}