{"id":"https://openalex.org/W7100854580","doi":null,"title":"Gaussian Processes in Practice Learning RoboCup-Keepaway with Kernels","display_name":"Gaussian Processes in Practice Learning RoboCup-Keepaway with Kernels","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7100854580"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.9328","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.9328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/%7Etjung/Neuer%20Ordner/gpip07.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7100854580"],"child_works_count":0,"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":null,"display_name":"Tobias Jung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070558949","display_name":"Daniel Polani","orcid":"https://orcid.org/0000-0002-3233-5847","observed_orcids":["https://orcid.org/0000-0002-3233-5847"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Polani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"D. Lawrence","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Lawrence","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010707054","display_name":"Anton Schwaighofer","orcid":"https://orcid.org/0000-0003-1557-0527","observed_orcids":["https://orcid.org/0000-0003-1557-0527"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anton Schwaighofer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050041093","display_name":"Joaquin Qui\u00f1onero C","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joaquin Qui\u00f1onero C","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":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/T12814","display_name":"Gaussian Processes and Bayesian Inference","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":9.999999747378752e-05,"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/simulated-soccer","display_name":"simulated soccer","score":0.8479999899864197},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8320000171661377},{"id":"https://openalex.org/keywords/kernel-methods","display_name":"kernel methods","score":0.6909999847412109},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.8240000009536743},{"id":"https://openalex.org/keywords/approximate-policy-iteration","display_name":"approximate policy iteration","score":0.7480000257492065},{"id":"https://openalex.org/keywords/regularization-networks","display_name":"regularization networks","score":0.949999988079071},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.6650000214576721},{"id":"https://openalex.org/keywords/high-dimensional-state-spaces","display_name":"high-dimensional state spaces","score":0.8159999847412109},{"id":"https://openalex.org/keywords/agent-cooperation","display_name":"agent cooperation","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7351999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6234999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942000150680542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5149000287055969},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.45320001244544983},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4237000048160553},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.42010000348091125},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3953000009059906},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37950000166893005},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2639000117778778},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.9328","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.9328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/%7Etjung/Neuer%20Ordner/gpip07.pdf","raw_type":"text"}],"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/W2136655982","https://openalex.org/W7100868110","https://openalex.org/W2104641222","https://openalex.org/W2155791599","https://openalex.org/W7099334297","https://openalex.org/W7099368663","https://openalex.org/W3008729385","https://openalex.org/W2103020053","https://openalex.org/W7098225630","https://openalex.org/W2919487069"],"abstract_inverted_index":{"We":[0,70],"apply":[1],"kernel-based":[2],"methods":[3],"to":[4,40,47],"solve":[5],"the":[6,23,26,37,51,55,72,89,122,130],"difficult":[7],"reinforcement":[8],"learning":[9,44,61],"problem":[10],"of":[11,25,54,75,91,96,101,114],"3vs2":[12],"keepaway":[13,21],"in":[14,20],"RoboCup":[15],"simulated":[16],"soccer.":[17],"Key":[18],"challenges":[19],"are":[22,57],"highdimensionality":[24],"state":[27],"space":[28],"(rendering":[29],"conventional":[30],"discretization-based":[31],"function":[32,85],"approximation":[33],"like":[34],"tilecoding":[35,135],"infeasible),":[36],"stochasticity":[38],"due":[39],"noise":[41],"and":[42,59],"multiple":[43],"agents":[45],"needing":[46],"cooperate":[48],"(meaning":[49,62],"that":[50,63,121],"exact":[52],"dynamics":[53],"environment":[56],"unknown)":[58],"real-time":[60],"an":[64,106],"efficient":[65,107],"online":[66],"implementation":[67,109],"is":[68,105],"required).":[69],"employ":[71],"general":[73],"framework":[74],"approximate":[76],"policy":[77,81],"iteration":[78],"with":[79,94,110,134],"least-squares-based":[80],"evaluation.":[82],"As":[83],"underlying":[84],"approximator":[86],"we":[87],"consider":[88],"family":[90],"regularization":[92],"networks":[93],"subset":[95],"regressors":[97],"approximation.":[98],"The":[99],"core":[100],"our":[102,126],"proposed":[103],"solution":[104],"recursive":[108],"automatic":[111],"supervised":[112],"selection":[113],"relevant":[115],"basis":[116],"functions.":[117],"Simulation":[118],"results":[119,132],"indicate":[120],"behavior":[123],"learned":[124],"through":[125],"approach":[127],"clearly":[128],"outperforms":[129],"best":[131],"obtained":[133],"by":[136],"Stone":[137],"et":[138],"al.":[139],"(2005).":[140]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2025-10-27T00:00:00"}