{"id":"W3045293119","doi":"10.48550/arxiv.2007.10916","title":"On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Convergence (economics); Mathematical optimization; Bellman equation; Monte Carlo method; Computer science; Complement (music); Markov decision process; Function (biology); Stochastic approximation; Applied mathematics; Mathematics; Markov process; Artificial intelligence; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.008696639,0.001574842,0.002397907,0.001508765,0.0009766119,0.001639846,0.002400978,0.001898637,0.005304918],"category_scores_gemma":[0.05709656,0.0009830307,0.001387163,0.000998235,0.004247706,0.003230611,0.003297286,0.003464647,0.0006290004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002551484,"about_ca_system_score_gemma":0.002730286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007153327,"about_ca_topic_score_gemma":0.003589896,"domain_scores_codex":[0.9964105,0.0021714,0.0001138722,0.0004161898,0.0005989356,0.0002890827],"domain_scores_gemma":[0.9484535,0.04561659,0.001587892,0.001158266,0.002154934,0.001028745],"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":[0.0001685286,0.00004900941,0.001036587,0.0001229895,0.0000741606,0.00007202054,0.0001769369,0.7873725,0.0004435422,0.198563,0.0008415439,0.01107914],"study_design_scores_gemma":[0.00001946698,0.00003228725,0.00009094881,0.00003799476,0.000009252586,0.00001267201,0.00001320255,0.9287726,0.0001388859,0.07051928,0.0003438141,0.000009567258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0251465,0.0008397241,0.9639114,0.0007570683,0.00006887343,0.00007648507,0.00006683035,0.0002242084,0.008908959],"genre_scores_gemma":[0.7940237,0.001722511,0.1944664,0.0004464375,0.0001592897,0.0005721147,0.000279052,0.0004679432,0.007862472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008696639,"threshold_uncertainty_score":0.04599279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1503308442699026,"score_gpt":0.1824893056548437,"score_spread":0.03215846138494108,"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."}}