{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000559185,0.0002686783,0.0002155668,0.0003423405,0.000521906,0.0008869543,0.000431123,0.000103971,0.000009272318],"category_scores_gemma":[0.0001952156,0.0002490108,0.00005385412,0.0005276361,0.00003206464,0.00638386,0.0001103189,0.0003180756,0.0001127762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003652751,"about_ca_system_score_gemma":0.0001143806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002693753,"about_ca_topic_score_gemma":6.808772e-8,"domain_scores_codex":[0.9974852,0.00009643027,0.0008133312,0.0001665076,0.000909243,0.0005293011],"domain_scores_gemma":[0.9983909,0.00008481972,0.0008192331,0.0002881663,0.0002527774,0.0001641703],"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":[0.000009596092,0.00001272217,0.000383099,0.0001478545,0.000006917232,2.067756e-7,0.001004467,0.9946883,0.0001922326,0.002074935,0.00003822269,0.001441444],"study_design_scores_gemma":[0.0005147515,0.0001692437,0.0000588558,0.0001908528,0.00001018285,0.00001268355,0.0001636032,0.997706,0.000524611,0.000004546228,0.0003742172,0.0002704605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0111565,0.00004103796,0.9859101,0.00003984713,0.001320555,0.000435029,6.203559e-7,0.0004168892,0.0006794616],"genre_scores_gemma":[0.9974749,4.81468e-7,0.001803049,0.0003163316,0.0001678937,0.00002515821,0.00007863174,0.00001641862,0.0001171538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9863184,"threshold_uncertainty_score":0.9999962,"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."}}