{"id":"W2996026485","doi":"10.48550/arxiv.1912.06875","title":"Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Booth University College","funders":"","keywords":"Curse of dimensionality; Reinforcement learning; Linear-quadratic regulator; Convergence (economics); Mathematical optimization; State space; Quadratic equation; Computer science; Action (physics); Mathematics; Optimal control; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003249212,0.0004771359,0.000560288,0.0002408476,0.0001899397,0.0002657744,0.003291243,0.0004380481,0.00002242951],"category_scores_gemma":[0.0002329169,0.0005327675,0.0004174461,0.0003864514,0.0001880267,0.00047461,0.002320432,0.0009765376,0.0001802873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003638292,"about_ca_system_score_gemma":0.0005295941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000031542,"about_ca_topic_score_gemma":0.000006234972,"domain_scores_codex":[0.997255,0.0001657608,0.0003622547,0.001315123,0.0002505017,0.0006513337],"domain_scores_gemma":[0.9968845,0.0004658982,0.0003283465,0.001755475,0.0003372121,0.0002285793],"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":[0.00004271173,0.00003109155,0.0008682985,0.0002686847,0.0001233949,0.00004833685,0.0001037005,0.8104618,0.00003682328,0.1873326,0.0005940229,0.00008855776],"study_design_scores_gemma":[0.0007583839,0.0001408306,0.0008060097,0.0001599968,0.00008379918,0.000003798731,0.00002574064,0.9878789,0.00008740242,0.007348969,0.00209665,0.0006095226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04424648,0.00008477506,0.9504699,0.0003466898,0.002923367,0.0008287021,0.00001256053,0.0003653711,0.0007221961],"genre_scores_gemma":[0.9786056,0.00005905737,0.01360274,0.0002856242,0.0001880984,0.000002082661,0.00005362862,0.00003490423,0.007168256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9368671,"threshold_uncertainty_score":0.9997124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05382236452644264,"score_gpt":0.2089326983325367,"score_spread":0.1551103338060941,"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."}}