{"id":"W2137312721","doi":"","title":"On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization","year":2012,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Kernel (algebra); Factorization; Q-learning; Markov process; Algorithm; State space; Mathematical optimization; Artificial intelligence; Mathematics","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":[0.001268521,0.0008984014,0.001268675,0.0003582067,0.000368516,0.0006352154,0.001481098,0.000967887,0.001817166],"category_scores_gemma":[0.005609119,0.000444442,0.0005417665,0.0002868109,0.0009970631,0.001131339,0.001232896,0.001604855,0.000319654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008928321,"about_ca_system_score_gemma":0.001499656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007127197,"about_ca_topic_score_gemma":0.005546447,"domain_scores_codex":[0.9994571,0.0001616778,0.00002693416,0.0001003173,0.0001748488,0.00007910941],"domain_scores_gemma":[0.9975794,0.001550889,0.0002374814,0.0002054419,0.0003134202,0.0001133806],"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":[0.00009474227,0.00009646386,0.0005199775,0.00004771975,0.00002667834,0.0000583151,0.00005583209,0.9461254,0.001459406,0.006452494,0.0005957516,0.04446721],"study_design_scores_gemma":[0.000007303422,0.00001675802,0.0000224733,0.000001538287,0.000001866187,0.000005927744,0.000001567374,0.9984,0.0002152011,0.001256148,0.00006912074,0.000002026724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02028822,0.00007556794,0.9781309,0.00007234803,0.00001723908,0.00005258304,0.00001664227,0.0004616726,0.0008847582],"genre_scores_gemma":[0.8266873,0.00007661138,0.1717175,0.00009635906,0.00002052335,0.0001591,0.00008656009,0.00006476316,0.00109124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007127197,"threshold_uncertainty_score":0.01417142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04506249051321851,"score_gpt":0.2865254556770245,"score_spread":0.241462965163806,"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."}}