{"id":"W2149385746","doi":"","title":"Direct value-approximation for factored MDPs","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov decision process; Bellman equation; Mathematical optimization; Linear programming; Linear approximation; Computation; Approximation error; Computer science; Approximation algorithm; Dynamic programming; Function (biology); Reduction (mathematics); Value (mathematics); Constraint (computer-aided design); Mathematics; Simple (philosophy); Applied mathematics; Markov process; Algorithm; Nonlinear system","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":[0.001704833,0.00131432,0.001947466,0.000707898,0.0003882085,0.0012609,0.001399272,0.001347368,0.004718922],"category_scores_gemma":[0.01049394,0.0007724179,0.001012915,0.0007068406,0.001214009,0.00187245,0.00138753,0.001938633,0.0006157474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001464623,"about_ca_system_score_gemma":0.001296623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004901025,"about_ca_topic_score_gemma":0.004938276,"domain_scores_codex":[0.999249,0.0002373932,0.00004365461,0.0001469449,0.0002227246,0.0001001853],"domain_scores_gemma":[0.9963163,0.002785677,0.0002246214,0.0002859579,0.0002793486,0.0001081472],"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":[0.00006694447,0.00003037649,0.0002472404,0.00007629821,0.00002258225,0.00004625223,0.00004092495,0.9478051,0.0003711769,0.02702302,0.0004722116,0.02379784],"study_design_scores_gemma":[0.00001132005,0.0000157851,0.00001591084,0.000007780104,0.000003307203,0.000006744095,0.000003475481,0.9811335,0.0001774114,0.01837894,0.0002431081,0.000002705657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006649993,0.0001371887,0.9917958,0.00005124379,0.0000165477,0.00003544521,0.00004369396,0.0002469605,0.001023146],"genre_scores_gemma":[0.5059766,0.0003871848,0.4904768,0.00009358148,0.00005056147,0.0004082951,0.0002774168,0.0001696459,0.002159825],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004901025,"threshold_uncertainty_score":0.01578641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02832180089933768,"score_gpt":0.2669645503386068,"score_spread":0.2386427494392691,"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."}}