{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00599298,0.00112789,0.001385266,0.001114993,0.0005666818,0.001530551,0.002028189,0.001818668,0.00280158],"category_scores_gemma":[0.03879693,0.0005616369,0.001094909,0.00065078,0.003031818,0.003002041,0.002744857,0.002691614,0.0004023402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001521296,"about_ca_system_score_gemma":0.001695167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002948103,"about_ca_topic_score_gemma":0.001475567,"domain_scores_codex":[0.9982431,0.0005964383,0.0001278521,0.0004022361,0.0004798137,0.0001506473],"domain_scores_gemma":[0.9850821,0.01089037,0.0009459664,0.000777973,0.001779021,0.0005244021],"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":[0.0002177102,0.0001017542,0.002669183,0.0002440151,0.00009709453,0.0001820252,0.0002197817,0.7263383,0.003662004,0.2448778,0.0006916923,0.02069863],"study_design_scores_gemma":[0.00001111958,0.0000346737,0.0000865622,0.0000139888,0.000004547766,0.00001787527,0.00000758754,0.9717881,0.0004726968,0.02737368,0.000180184,0.000008965323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0328254,0.0002749486,0.9640053,0.000345799,0.00003788005,0.00005851728,0.00005684409,0.0001131053,0.002282234],"genre_scores_gemma":[0.7757737,0.0005493936,0.2174491,0.0004527618,0.00007784081,0.0004724268,0.0002653617,0.0001704847,0.00478894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00599298,"threshold_uncertainty_score":0.03169429,"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."}}