{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002498238,0.0001253149,0.0001187387,0.0002741198,0.0001155231,0.0006439303,0.0003424369,0.00006015813,0.0001334034],"category_scores_gemma":[0.0007817723,0.0001293693,0.00002503488,0.0003037145,0.00003465868,0.001241943,0.0001990464,0.0002829858,0.0000127473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001086639,"about_ca_system_score_gemma":0.0001573965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001010134,"about_ca_topic_score_gemma":0.00004335465,"domain_scores_codex":[0.9987917,0.0001136449,0.00031796,0.0003326308,0.0002928047,0.0001512821],"domain_scores_gemma":[0.9991965,0.00006214756,0.0001763541,0.0002268769,0.0002842033,0.00005391729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006951272,0.00006526076,0.006161847,0.00001322994,0.00002047,0.00005662948,0.008518128,0.009240217,0.01755689,0.9109563,0.00003300767,0.04730856],"study_design_scores_gemma":[0.0005846003,0.00004455439,0.002494855,0.00005387366,6.928429e-7,0.00004555688,0.0001356872,0.9916584,0.001765884,0.00210566,0.0009694129,0.0001408282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1511841,0.00005384723,0.7880596,0.01849877,0.0004884314,0.0002245408,0.000005091623,0.0002337446,0.04125189],"genre_scores_gemma":[0.9700242,0.00007144042,0.02676416,0.0007276516,0.00005379596,0.00001760523,0.00007154986,0.000006901565,0.002262716],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9824182,"threshold_uncertainty_score":0.6209435,"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."}}