{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002288927,0.0003215821,0.0006798676,0.000809146,0.0001260608,0.00009863263,0.002944174,0.0002412245,0.0001057461],"category_scores_gemma":[0.0000767185,0.0003888193,0.0005794804,0.002564791,0.0001006692,0.0002670263,0.003282337,0.0006324863,0.00005726325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001586039,"about_ca_system_score_gemma":0.0001200562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043568,"about_ca_topic_score_gemma":0.00001478007,"domain_scores_codex":[0.997897,0.0001329568,0.0003581114,0.001089038,0.0001900946,0.000332828],"domain_scores_gemma":[0.9973279,0.0001240118,0.0006388791,0.001558126,0.0001698988,0.0001812442],"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":[0.000009607676,0.00002093192,0.002969461,0.00007142426,0.001116417,0.00008938624,0.0004592466,0.9432046,0.00002842869,0.05189941,0.00007591953,0.00005513618],"study_design_scores_gemma":[0.0002033378,0.00004418465,0.001762501,0.00006203567,0.0009795061,4.262177e-7,0.00006597821,0.9949796,0.00008806476,0.001163353,0.0002993123,0.0003516508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02727165,0.00001971977,0.9656212,0.0001731113,0.0002839211,0.0001851007,0.0000104215,0.0002381175,0.006196751],"genre_scores_gemma":[0.993134,0.00004172563,0.005486444,0.0001038584,0.00003212075,3.827913e-7,0.00003825236,0.00001843215,0.001144826],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9658623,"threshold_uncertainty_score":0.9998564,"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."}}