{"id":"W3040829104","doi":"10.48550/arxiv.2007.03749","title":"Sharp Analysis of Smoothed Bellman Error Embedding","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Embedding; Bellman equation; Artificial neural network; Function (biology); Representation (politics); Horizon; Computer science; Nonlinear system; Algorithm; Mathematics; Discrete mathematics; Applied mathematics; Mathematical optimization; Physics; Artificial intelligence; Quantum mechanics; Geometry","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":[0.003397952,0.001186643,0.001186201,0.0007001674,0.0005887247,0.001332897,0.001642279,0.001872769,0.004408114],"category_scores_gemma":[0.0208414,0.0006408604,0.0006742728,0.000479097,0.00254709,0.002688411,0.002837267,0.003606194,0.0005937933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001926564,"about_ca_system_score_gemma":0.001839561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002210729,"about_ca_topic_score_gemma":0.001636783,"domain_scores_codex":[0.9985176,0.0005588228,0.00005628376,0.0002829579,0.000400039,0.0001843291],"domain_scores_gemma":[0.990276,0.006840858,0.0006993486,0.0007235066,0.0009730062,0.0004873458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003216538,0.000070783,0.001126649,0.0001986965,0.00006435376,0.0001138465,0.0001677279,0.6555449,0.005062369,0.3057272,0.003083868,0.02851792],"study_design_scores_gemma":[0.00001186765,0.00005001106,0.0001142613,0.0000153643,0.000004896303,0.00001341448,0.000006944212,0.9559844,0.0007214076,0.04270732,0.0003616605,0.000008582222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03984116,0.0004045695,0.9534352,0.0007306514,0.00007074132,0.00004614478,0.00008840853,0.0004378153,0.004945247],"genre_scores_gemma":[0.8593358,0.00039084,0.1298861,0.0004599344,0.00009396894,0.0002276525,0.0002371688,0.0002957146,0.009072911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004408114,"threshold_uncertainty_score":0.01797032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1156203499844863,"score_gpt":0.22891043717234,"score_spread":0.1132900871878537,"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."}}