{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001023678,0.0002884124,0.0002353148,0.0003367213,0.0002714601,0.000553911,0.001321144,0.0002117419,0.00002742626],"category_scores_gemma":[0.0001844255,0.0002925817,0.0001307388,0.0006245667,0.00004643416,0.00258646,0.0005028097,0.0003917614,0.0001665765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003770159,"about_ca_system_score_gemma":0.0000934204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008733834,"about_ca_topic_score_gemma":0.00002584606,"domain_scores_codex":[0.9974764,0.0001586894,0.0004287058,0.0003501023,0.0006078966,0.0009781865],"domain_scores_gemma":[0.9979965,0.0001079626,0.000221037,0.001197818,0.000092628,0.0003840226],"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":[0.000012679,0.0001745557,0.08069158,0.00002952902,0.00004299997,0.00001668254,0.001591739,0.09819986,0.004772442,0.7774394,0.004056316,0.03297218],"study_design_scores_gemma":[0.00028928,0.0001201607,0.06547137,0.00003418754,0.00001644697,0.0001018448,0.00002071859,0.9081851,0.006653749,0.001148693,0.01747243,0.0004859545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006366373,0.0005898154,0.9855387,0.003228568,0.0005121448,0.0005412074,0.000001840549,0.001188668,0.002032681],"genre_scores_gemma":[0.7013289,0.00004721117,0.2932582,0.003694384,0.000336475,0.0002409449,0.0000109321,0.00003328179,0.001049655],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8099853,"threshold_uncertainty_score":0.9999526,"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."}}