{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009928298,0.001166533,0.0009900328,0.0005337849,0.0003896185,0.0009480074,0.001062312,0.001109519,0.002370292],"category_scores_gemma":[0.003897935,0.0008353175,0.0006733557,0.0004683057,0.001287392,0.001582852,0.001399526,0.001492682,0.000330416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001210317,"about_ca_system_score_gemma":0.001686159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00762059,"about_ca_topic_score_gemma":0.006922528,"domain_scores_codex":[0.9995129,0.0002045456,0.0000219004,0.0001107354,0.00009591095,0.00005402178],"domain_scores_gemma":[0.9985368,0.001140446,0.0000915968,0.0001059288,0.00008105575,0.00004416905],"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":[0.00002644253,0.00002245679,0.0001947831,0.00002850155,0.00001352243,0.00002168819,0.0000211857,0.9800003,0.0003598287,0.006703395,0.0002643972,0.0123435],"study_design_scores_gemma":[0.000005373875,0.000007265098,0.00001299514,0.000002516711,0.000001754186,0.000002451147,0.00000232168,0.995417,0.0001138596,0.004285785,0.000147432,0.000001310304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03235261,0.0002968825,0.9634911,0.0003202791,0.00003097321,0.00004497534,0.00006589174,0.0008455533,0.002551681],"genre_scores_gemma":[0.7826213,0.0003476405,0.2137403,0.0002119905,0.00003988898,0.000305486,0.0002348996,0.0001915484,0.0023069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00762059,"threshold_uncertainty_score":0.01515251,"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."}}