{"id":"https://openalex.org/W2109718666","doi":null,"title":"Online Feature Discovery in Relational Reinforcement Learning","display_name":"Online Feature Discovery in Relational Reinforcement Learning","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2109718666","mag":"2109718666"},"language":"en","primary_location":{"id":"mag:2109718666","doi":null,"is_oa":false,"landing_page_url":"http://users.cecs.anu.edu.au/~ssanner/Papers/icml06_srl_ws.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},"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/A5028174137","display_name":"Scott Sanner","orcid":"https://orcid.org/0000-0001-7984-8394","observed_orcids":["https://orcid.org/0000-0001-7984-8394"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Scott Sanner","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7984-8394","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5028174137"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3536,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69752679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"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":0.989300012588501,"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":0.989300012588501,"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":0.006899999920278788,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0020000000949949026,"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/relational-reinforcement-learning","display_name":"relational reinforcement learning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.7360000014305115},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/frequent-itemset-mining","display_name":"frequent itemset mining","score":0.7699999809265137},{"id":"https://openalex.org/keywords/apriori-algorithm","display_name":"Apriori algorithm","score":0.953000009059906},{"id":"https://openalex.org/keywords/tic-tac-toe","display_name":"Tic-Tac-Toe","score":0.7009999752044678},{"id":"https://openalex.org/keywords/backgammon","display_name":"backgammon","score":0.9959999918937683},{"id":"https://openalex.org/keywords/othello","display_name":"Othello","score":1.0}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6921563148498535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6041222810745239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979025363922119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5709743499755859},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47331011295318604},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46698421239852905},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.439191997051239},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4168437123298645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3063521385192871},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.24348905682563782},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2109718666","doi":null,"is_oa":false,"landing_page_url":"http://users.cecs.anu.edu.au/~ssanner/Papers/icml06_srl_ws.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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W106493965","https://openalex.org/W1484413656","https://openalex.org/W1497290640","https://openalex.org/W1536655300","https://openalex.org/W1543809641","https://openalex.org/W1689445748","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2126185296","https://openalex.org/W2158282517","https://openalex.org/W2168359464","https://openalex.org/W2396715201","https://openalex.org/W2521075165","https://openalex.org/W3020831056"],"related_works":["https://openalex.org/W7100372836","https://openalex.org/W7098021569","https://openalex.org/W42392872","https://openalex.org/W3004806417","https://openalex.org/W30507863","https://openalex.org/W4253865213","https://openalex.org/W7100943048","https://openalex.org/W2152669282","https://openalex.org/W4416118775","https://openalex.org/W7096000326"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,25,85],"technique":[3],"for":[4],"model-free":[5],"relational":[6,27],"reinforcement":[7],"learning":[8,39,66,87,94,113],"in":[9,78,137],"indefinite":[10],"horizon":[11],"undiscounted":[12],"domains":[13,140],"with":[14],"bounded":[15],"reward.":[16],"Previous":[17],"work":[18],"has":[19,32,115],"represented":[20],"the":[21,46,96,105,116,127,138],"value":[22,47,51],"function":[23,52],"as":[24],"ground":[26],"naive":[28,70],"Bayes":[29,34,71,91],"net":[30,35,72,92],"and":[31,37,54,121,144],"leveraged":[33],"parameter":[36,55,123],"structure":[38,73,93,112],"techniques":[40],"to":[41],"refine":[42],"successive":[43],"approximations":[44],"of":[45,67,100,119,129,141],"function.":[48],"Unfortunately,":[49],"while":[50],"evaluation":[53],"inference":[56],"are":[57],"very":[58],"efficient":[59],"under":[60],"this":[61,81,111,130],"framework,":[62],"even":[63],"greedy":[64],"optimal":[65],"highly":[68],"restricted":[69],"can":[74],"be":[75],"computationally":[76],"prohibitive":[77],"practice.":[79],"In":[80],"paper,":[82],"we":[83,132],"propose":[84],"novel":[86],"algorithm":[88,114],"that":[89],"focuses":[90],"on":[95],"frequently":[97],"visited":[98],"portions":[99],"state":[101],"space.":[102],"Inspired":[103],"by":[104],"Apriori":[106],"frequent-itemset":[107],"data":[108],"mining":[109],"algorithm,":[110],"dual":[117],"benefits":[118],"efficiency":[120],"low-variance":[122],"estimates.":[124],"To":[125],"demonstrate":[126],"efficacy":[128],"approach,":[131],"present":[133],"encouraging":[134],"initial":[135],"results":[136],"game":[139],"TicTac-Toe,":[142],"Backgammon,":[143],"Othello.":[145]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2016-06-24T00:00:00"}