{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001995523,0.0001556102,0.0001219093,0.0001490889,0.0001830044,0.0001111071,0.0005282627,0.00005966243,0.0002528761],"category_scores_gemma":[0.00009629982,0.0001468255,0.00005110684,0.0003217435,0.00002950625,0.0004862021,0.0001626681,0.000169974,0.0001151998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023093,"about_ca_system_score_gemma":0.00009330278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006344281,"about_ca_topic_score_gemma":5.165226e-7,"domain_scores_codex":[0.9987099,0.00004840248,0.000283412,0.0002753884,0.0003634458,0.000319436],"domain_scores_gemma":[0.9991885,0.00004869661,0.0001671946,0.0003944622,0.0001059129,0.00009518894],"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":[0.000003258005,0.000008426178,0.0008515889,0.000006468392,0.000008391076,0.000001909151,0.000504482,0.9853175,0.000333941,0.0126017,0.000009289567,0.0003530023],"study_design_scores_gemma":[0.0002528676,0.0001310497,0.0003656944,0.00001967548,0.000007392981,0.00000186278,0.00002787814,0.9969632,0.001826725,0.0001017058,0.0001117679,0.0001901759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001421037,0.000004203093,0.9899817,0.00001411867,0.0003426088,0.0001592386,3.001685e-8,0.0003755287,0.007701559],"genre_scores_gemma":[0.9080668,4.685234e-7,0.09060805,0.0001208973,0.00002744229,0.000003842908,0.000003711738,0.00001314623,0.001155653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9066458,"threshold_uncertainty_score":0.5987371,"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."}}