{"id":"W2964112145","doi":"","title":"Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Iterated function; Convergence (economics); Markov decision process; Markov chain; Mathematics; Weak convergence; Constant (computer programming); Ergodic theory; Applied mathematics; Divergence (linguistics); Rate of convergence; Limit (mathematics); Stochastic approximation; Markov process; Mathematical optimization; Computer science; Key (lock); Mathematical analysis; 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":[],"consensus_categories":[],"category_scores_codex":[0.005013146,0.0002394544,0.0005455358,0.0005090158,0.0003824595,0.0002781364,0.001053195,0.00008988054,0.00004224577],"category_scores_gemma":[0.004463488,0.0001364396,0.00007918409,0.0005774282,0.0009105948,0.0007533361,0.0004775556,0.001490702,0.000007703147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009295855,"about_ca_system_score_gemma":0.0005817413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006953876,"about_ca_topic_score_gemma":0.000005393544,"domain_scores_codex":[0.9952306,0.001184055,0.0008706066,0.0003528706,0.001765835,0.0005960707],"domain_scores_gemma":[0.9955349,0.001737736,0.0009328045,0.000330327,0.00120448,0.0002597593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000763562,0.0001354273,0.714509,0.0006088418,0.0003305523,0.0002741014,0.005765186,0.03568071,0.1920551,0.007446728,0.0000590596,0.04237182],"study_design_scores_gemma":[0.01358927,0.02173246,0.04688054,0.01806772,0.0001332882,0.003037219,0.005186555,0.8441844,0.03958356,0.0009523251,0.004825151,0.001827525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6905428,0.000757149,0.3055547,0.002142891,0.0001099103,0.0002313389,6.458457e-7,0.00005140738,0.0006091964],"genre_scores_gemma":[0.9850425,0.0004383789,0.01229681,0.0000148091,0.00004251771,0.000003441208,3.225768e-7,0.00002421499,0.002136998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8085037,"threshold_uncertainty_score":0.6476443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05478746984954716,"score_gpt":0.3014922333272734,"score_spread":0.2467047634777262,"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."}}