{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003007391,0.0008017176,0.001923236,0.0006430062,0.000617752,0.001294702,0.001898532,0.002066947,0.005232531],"category_scores_gemma":[0.01209502,0.001063991,0.0009238911,0.00124598,0.001658341,0.001370119,0.002001199,0.002298601,0.0007415939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001018806,"about_ca_system_score_gemma":0.001801341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008837162,"about_ca_topic_score_gemma":0.006688266,"domain_scores_codex":[0.9990185,0.0005145009,0.00005032802,0.0001560651,0.0001968975,0.00006365791],"domain_scores_gemma":[0.9936773,0.004867421,0.0001749603,0.0003349314,0.0007685036,0.0001768062],"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":[0.0001393171,0.00005865655,0.0002362667,0.0001332447,0.0000305362,0.00005329058,0.0001181808,0.8779224,0.0008107251,0.04440263,0.002315019,0.07377976],"study_design_scores_gemma":[0.000007151809,0.000009700966,0.00001188565,0.000003369183,0.000001886598,0.00000458135,0.000003069458,0.9919525,0.0001501801,0.007580435,0.0002721748,0.000003006524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002748126,0.0001134052,0.995822,0.00005692802,0.00003130768,0.00001591304,0.00001846595,0.0002745407,0.0009192003],"genre_scores_gemma":[0.1599827,0.0001807534,0.8353561,0.00007417773,0.00005572168,0.0001447578,0.00009270254,0.0004067891,0.003706308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008837162,"threshold_uncertainty_score":0.01757145,"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."}}