{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004333836,0.0009971182,0.00179438,0.0005977907,0.0004997684,0.001271118,0.0019362,0.002194867,0.002204964],"category_scores_gemma":[0.01910344,0.0009082287,0.0008128828,0.0006962336,0.003256886,0.002201631,0.001577053,0.002137963,0.0003959892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00172397,"about_ca_system_score_gemma":0.001668487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004786164,"about_ca_topic_score_gemma":0.002517279,"domain_scores_codex":[0.9981568,0.000971316,0.00007051754,0.000276726,0.0003354791,0.0001890812],"domain_scores_gemma":[0.9884686,0.009002777,0.0007130791,0.000454944,0.0007976193,0.0005629124],"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":[0.0001174317,0.00003950673,0.0003652794,0.00004181952,0.00002432946,0.00005630873,0.00005120328,0.9681436,0.000325541,0.025433,0.0002027691,0.005199137],"study_design_scores_gemma":[0.00001679392,0.00003165851,0.00002793409,0.00000427714,0.000002481004,0.000006165576,0.000004523295,0.9901957,0.0001118599,0.009494732,0.0001004335,0.000003356919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03745475,0.0002183296,0.9604027,0.0002049564,0.0000293085,0.00004992067,0.00003415233,0.0002189856,0.001386906],"genre_scores_gemma":[0.8110002,0.000216002,0.1851416,0.0001320173,0.00003987824,0.0002702385,0.0001226414,0.0001010972,0.002976307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004786164,"threshold_uncertainty_score":0.02291983,"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."}}