{"id":"W2111625536","doi":"","title":"Value Pursuit Iteration","year":2012,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bellman equation; Reinforcement learning; Value (mathematics); Function (biology); Set (abstract data type); Mathematics; Algorithm; Power iteration; Mathematical optimization; Representation (politics); Approximation error; Computer science; Iterative method; Approximation algorithm; Artificial intelligence; 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":[0.002777504,0.001502845,0.002179615,0.0007773086,0.0008517262,0.001983149,0.001708583,0.001963615,0.006646809],"category_scores_gemma":[0.01403938,0.0006662809,0.0008850553,0.0008346173,0.002212553,0.002058533,0.003315741,0.002939257,0.00195151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001417592,"about_ca_system_score_gemma":0.002383736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001711825,"about_ca_topic_score_gemma":0.001423827,"domain_scores_codex":[0.9977532,0.0007713995,0.0001156262,0.0003987919,0.0007034642,0.0002575369],"domain_scores_gemma":[0.9948562,0.003329125,0.0002842499,0.0004503908,0.0008563997,0.0002235597],"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":[0.0003209208,0.0001729927,0.0011175,0.000321419,0.0001289985,0.0001770781,0.0001786107,0.5211072,0.003056049,0.2733959,0.008300462,0.1917229],"study_design_scores_gemma":[0.00003290454,0.00007072269,0.0000622089,0.00003189007,0.00000988718,0.0000437926,0.0000158837,0.9417807,0.001196055,0.05367436,0.003070016,0.00001153917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003272919,0.0003000762,0.9897202,0.0001841136,0.00006098604,0.00006701226,0.00002483986,0.0002130165,0.006156876],"genre_scores_gemma":[0.4078645,0.001074434,0.5717044,0.0005185254,0.0001999869,0.0006414736,0.0003304526,0.0004215349,0.01724467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006646809,"threshold_uncertainty_score":0.02223581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01302020770483617,"score_gpt":0.2378196010938633,"score_spread":0.2247993933890272,"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."}}