{"id":"W2097575529","doi":"","title":"Reinforcement Learning using Kernel-Based Stochastic Factorization","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Kernel (algebra); Factorization; Markov decision process; Scalability; Matrix decomposition; Artificial intelligence; Machine learning; Algorithm; Markov process; Mathematics; Eigenvalues and eigenvectors","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002185206,0.0008993346,0.001506786,0.0005188151,0.0003565871,0.0007065295,0.0009833327,0.001008004,0.001448884],"category_scores_gemma":[0.00814984,0.0005117191,0.0006029271,0.0004312094,0.001255769,0.001331877,0.001072087,0.001677597,0.0003012504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001123871,"about_ca_system_score_gemma":0.001556515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004909961,"about_ca_topic_score_gemma":0.003149281,"domain_scores_codex":[0.9991442,0.0003605451,0.00005205694,0.000137399,0.0002128953,0.00009297817],"domain_scores_gemma":[0.9958442,0.002972446,0.0003393929,0.0002151271,0.000499309,0.0001295213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005827739,0.00003718767,0.0003911825,0.00004968213,0.00002825217,0.00003500999,0.00003841793,0.9628912,0.001020142,0.01181782,0.0003661364,0.02326654],"study_design_scores_gemma":[0.000005513793,0.00001066909,0.00001823797,0.000001741341,0.000001520055,0.000003429873,0.000001152138,0.9974983,0.0001263619,0.002278179,0.00005297925,0.000001926566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007439903,0.00007324456,0.9918434,0.00006514456,0.00001130885,0.00002391104,0.00001089197,0.0001729828,0.0003591173],"genre_scores_gemma":[0.7889496,0.0001886824,0.2088969,0.0001015853,0.00004015902,0.000202587,0.0001034594,0.00006846606,0.001448503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004909961,"threshold_uncertainty_score":0.01155663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0600288240839159,"score_gpt":0.2556550448293221,"score_spread":0.1956262207454062,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}