{"id":"W2128812357","doi":"","title":"Error Propagation for Approximate Policy and Value Iteration","year":2010,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Value (mathematics); Computer science; Mathematical optimization; Algorithm; Mathematics; Machine learning","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001207163,0.000569424,0.0005052505,0.0008113928,0.0003911356,0.001468831,0.001394368,0.0009979499,0.000002966313],"category_scores_gemma":[0.0007681039,0.0005902785,0.0001755852,0.000368411,0.0001062335,0.0006898278,0.001618568,0.001373719,0.00000531463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004895136,"about_ca_system_score_gemma":0.0008055276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001838492,"about_ca_topic_score_gemma":0.0001880946,"domain_scores_codex":[0.9968324,0.0001550558,0.0007271074,0.0009951039,0.0005070195,0.0007832728],"domain_scores_gemma":[0.9968113,0.0001952779,0.0007259752,0.001697274,0.0002848264,0.0002853187],"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":[0.00003479986,0.00007894466,0.0006545929,0.0004670693,0.00006154795,0.000007237335,0.000842873,0.4224377,0.006286087,0.5507066,0.0006768217,0.01774578],"study_design_scores_gemma":[0.0003687122,0.0001412042,0.001183825,0.0001136562,0.00003189916,0.00004191695,0.000008990271,0.9719033,0.005304757,0.01793629,0.002394459,0.0005709543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004994018,0.0001801314,0.9824992,0.007239315,0.0004863556,0.003034835,0.00003622268,0.001170828,0.0003590322],"genre_scores_gemma":[0.2522911,0.0001051237,0.7420113,0.001763101,0.000548629,0.001952829,0.0002192599,0.00009471778,0.001013918],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5494657,"threshold_uncertainty_score":0.9996549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01625520364976859,"score_gpt":0.2649227238120397,"score_spread":0.2486675201622711,"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."}}