{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001855249,0.00008115468,0.00008762164,0.00005666135,0.000087469,0.000141382,0.0004168083,0.00003696137,0.00002853945],"category_scores_gemma":[0.0000892672,0.00006905665,0.00005014611,0.0001789993,0.00001150527,0.0003972516,0.0000726764,0.00003924503,0.00006517342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003443528,"about_ca_system_score_gemma":0.00002090093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001008578,"about_ca_topic_score_gemma":7.586802e-7,"domain_scores_codex":[0.9992463,0.00001958043,0.0001508373,0.0001946038,0.0001849088,0.0002037486],"domain_scores_gemma":[0.9993972,0.0001102209,0.00005943455,0.0003305227,0.00005748336,0.0000451398],"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":[0.00001164713,0.0000436136,0.002017357,0.0000286339,0.00003471562,0.00000262451,0.0006989564,0.6270947,0.001449412,0.3368144,0.006792475,0.0250114],"study_design_scores_gemma":[0.0002321998,0.00007171811,0.0008479306,0.00000464174,0.000002857937,0.00000250717,0.000008841869,0.9661146,0.002641374,0.0008301081,0.02913212,0.0001110466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009417756,0.000006879396,0.9439813,0.0003833771,0.0002388917,0.0002349265,2.145772e-7,0.0003015996,0.05391106],"genre_scores_gemma":[0.6180343,0.00001089694,0.3667979,0.0004037589,0.00007817559,0.00003348648,0.000009311402,0.00001151437,0.01462064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6170925,"threshold_uncertainty_score":0.2816049,"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."}}