{"id":"W2950564923","doi":"10.48550/arxiv.1906.08649","title":"Exploring Model-based Planning with Policy Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Benchmarking; Computer science; Code (set theory); Artificial neural network; Sample (material); Control (management); Action (physics); Artificial intelligence; Mathematical optimization; Optimization problem; State space; Machine learning; Algorithm; Mathematics","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":[0.0001927242,0.0004034093,0.0003589202,0.0004869909,0.0001676702,0.0002292147,0.002183192,0.0002141443,0.000003720559],"category_scores_gemma":[0.00002169282,0.0004377587,0.0001435196,0.0007479093,0.00007868203,0.0006884305,0.001643101,0.0009749728,0.00004466275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003669396,"about_ca_system_score_gemma":0.0006287905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000694086,"about_ca_topic_score_gemma":0.00000184395,"domain_scores_codex":[0.997942,0.00007962192,0.000194803,0.001051301,0.0001540731,0.0005782297],"domain_scores_gemma":[0.9975359,0.0001152606,0.0003268853,0.00170831,0.0001340256,0.0001795886],"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":[0.00002677826,0.00001359031,0.00297357,0.00005490653,0.00005303891,0.0001199926,0.0001752361,0.9597287,9.86561e-7,0.03672935,0.0000334651,0.00009037317],"study_design_scores_gemma":[0.0004682041,0.00007904929,0.0002480589,0.0002992741,0.0000348566,0.000001629022,0.00002585047,0.9977442,0.00001721438,0.0004897301,0.00007682095,0.0005151213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02098913,0.0000166304,0.9735274,0.00007113989,0.0003761999,0.0002873595,0.000001190012,0.0004313581,0.004299612],"genre_scores_gemma":[0.9872798,0.00003816171,0.01091352,0.0001854915,0.0001185366,0.00000194702,0.00001425591,0.00003846306,0.001409811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9662907,"threshold_uncertainty_score":0.9998074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1953208765541703,"score_gpt":0.2071532025152774,"score_spread":0.01183232596110709,"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."}}