{"id":"W3168197022","doi":"","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Age of Information Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Computer science; Function (biology); Computation; Mathematical optimization; Upper and lower bounds; Bellman equation; Simple (philosophy); Function approximation; Algorithm; Markov process; Mathematics; Artificial neural network; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004828817,0.001231411,0.001985062,0.0005385713,0.0006727711,0.001648295,0.002529372,0.001784033,0.00343134],"category_scores_gemma":[0.02814006,0.0007238632,0.000926053,0.0006002923,0.002247316,0.004125022,0.002488359,0.0035226,0.0006320706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001801787,"about_ca_system_score_gemma":0.002501205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003609546,"about_ca_topic_score_gemma":0.002116115,"domain_scores_codex":[0.9967787,0.001491645,0.0001368479,0.0005710836,0.0006219655,0.0003997748],"domain_scores_gemma":[0.9886207,0.008223229,0.0006222662,0.001358017,0.0008348473,0.0003408586],"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":[0.0004523722,0.0001438436,0.001070202,0.0000996635,0.00007135309,0.00009884548,0.0001230148,0.9183649,0.001225601,0.04594751,0.001209307,0.03119329],"study_design_scores_gemma":[0.00001519351,0.0000481677,0.00003920648,0.000006004291,0.000004180141,0.00001192426,0.000005144678,0.9897643,0.0003832482,0.009585139,0.0001337072,0.000003832356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0331207,0.0003729427,0.962468,0.0004651952,0.00005836627,0.0000659592,0.00004524282,0.0007020306,0.002701537],"genre_scores_gemma":[0.766412,0.0002545462,0.2286688,0.0003775495,0.00008734703,0.0002753256,0.0001640621,0.0002720882,0.003488346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004828817,"threshold_uncertainty_score":0.02553749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01873194199094811,"score_gpt":0.2950064456519339,"score_spread":0.2762745036609858,"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."}}