{"id":"W2151416233","doi":"","title":"Fitted Q-iteration in continuous action-space MDPs","year":2007,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Action (physics); Q-learning; Bellman equation; Trajectory; Set (abstract data type); Mathematical optimization; Action selection; Markov decision process; State space; Computer science; State (computer science); Function (biology); Value (mathematics); Space (punctuation); Selection (genetic algorithm); Mathematics; Algorithm; Artificial intelligence; Markov process; Machine learning; 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":[0.005217011,0.0001677522,0.0001749849,0.0002739896,0.0002268912,0.0004198458,0.0009865747,0.0001133806,0.00004201011],"category_scores_gemma":[0.001014889,0.0001859539,0.00006643419,0.0008924998,0.00007896763,0.0005789692,0.0003028178,0.000312473,0.00007901937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001359155,"about_ca_system_score_gemma":0.00008343826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003220356,"about_ca_topic_score_gemma":0.0009546096,"domain_scores_codex":[0.9970326,0.001313778,0.0004366607,0.0004358103,0.0003965472,0.000384535],"domain_scores_gemma":[0.9964423,0.001159999,0.0002689856,0.001188625,0.0008198653,0.0001201979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000260956,0.0005725659,0.03402884,0.0000694524,0.00004901227,0.00004200169,0.02678034,0.01781843,0.02342452,0.7442088,0.001980343,0.1509997],"study_design_scores_gemma":[0.001664039,0.000002274053,0.07118583,0.0006460989,0.00001176881,0.00003463452,0.0003172366,0.7491357,0.1308582,0.001602063,0.04381804,0.0007240969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05295417,0.00007786212,0.9087112,0.00454998,0.0001914444,0.000206702,6.722555e-7,0.0002433649,0.0330646],"genre_scores_gemma":[0.899999,0.00004884682,0.09045593,0.0001598524,0.00001559217,0.000009687915,0.00003145083,0.00001584571,0.009263756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8470449,"threshold_uncertainty_score":0.758298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0137757595605324,"score_gpt":0.2404128600699891,"score_spread":0.2266371005094567,"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."}}