{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002743899,0.0003405271,0.0003454337,0.0001466384,0.000208467,0.00009308876,0.002052031,0.0001029799,0.00004381278],"category_scores_gemma":[0.000105288,0.0002853318,0.0001472791,0.00054006,0.0001440175,0.0003398372,0.001924921,0.00103992,0.00005160519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001665619,"about_ca_system_score_gemma":0.0001888078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001367033,"about_ca_topic_score_gemma":0.000005309287,"domain_scores_codex":[0.9980998,0.0001663643,0.0002808926,0.0007996008,0.000299866,0.0003534977],"domain_scores_gemma":[0.997648,0.0002747392,0.0005462858,0.001205988,0.0001884931,0.0001364936],"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":[0.00004425055,0.000008933722,0.001338845,0.00006488892,0.000103046,0.00009035808,0.0009983582,0.8764602,0.00001405295,0.1207808,0.00006859087,0.00002770111],"study_design_scores_gemma":[0.000273838,0.0003816333,0.0002793435,0.0002635533,0.00004569818,9.799659e-7,0.0003136515,0.9967436,0.0004132176,0.0006468667,0.0003128876,0.0003247713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.175825,0.00001019049,0.8207959,0.0002137643,0.000307713,0.0003498056,7.947392e-7,0.0001651378,0.002331698],"genre_scores_gemma":[0.9977723,0.0001384354,0.0006186785,0.0001150985,0.000028286,0.000003259995,0.000002857731,0.00002156899,0.001299536],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8219473,"threshold_uncertainty_score":0.9999599,"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."}}