{"id":"W2167999092","doi":"10.1007/978-3-540-89722-4_5","title":"Regularized Fitted Q-Iteration: Application to Planning","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Control Systems and Identification","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Subroutine; Computer science; Mathematical optimization; Hilbert space; Reproducing kernel Hilbert space; Kernel (algebra); Markov decision process; Simple (philosophy); Function (biology); Algorithm; Applied mathematics; Markov process; Mathematics; Discrete mathematics; Statistics","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":[0.0001902245,0.0002143562,0.000242412,0.0003978834,0.0001135593,0.0001615899,0.0003797156,0.0001619658,0.000007065129],"category_scores_gemma":[0.0000181736,0.0002221614,0.00004430426,0.0002471933,0.00005651654,0.0001459255,0.00005994277,0.0002287982,0.00006015596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001996813,"about_ca_system_score_gemma":0.0000446694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009736809,"about_ca_topic_score_gemma":0.00002372515,"domain_scores_codex":[0.9986671,0.000006299915,0.0003189633,0.0004641197,0.0003339234,0.0002095539],"domain_scores_gemma":[0.999204,0.00005692276,0.00006440801,0.0004994543,0.0001022314,0.00007297006],"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":[0.000005196072,0.000004240357,0.00002451902,0.00004521632,0.000009923729,0.00001013471,0.001021467,0.628152,0.01227049,0.0003703256,0.0003735484,0.3577129],"study_design_scores_gemma":[0.0001762532,0.00002273568,0.0005819103,0.0002851114,0.000004757048,0.00002557898,7.92588e-8,0.9783294,0.0008515287,0.001786609,0.01757513,0.0003609069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004698322,0.0003908588,0.9959913,0.0001479115,0.0008195366,0.0004632488,0.000003272943,0.0001805757,0.001533417],"genre_scores_gemma":[0.9505549,0.00002667045,0.04675065,0.0003450706,0.00127229,0.00006914662,0.00005024938,0.00006385898,0.0008671799],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.950085,"threshold_uncertainty_score":0.9059479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01005746329751429,"score_gpt":0.2141080455470367,"score_spread":0.2040505822495224,"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."}}