{"id":"W2996347495","doi":"","title":"Exploring Model-based Planning with Policy Networks","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Benchmarking; Artificial neural network; Code (set theory); Artificial intelligence; Mathematical optimization; Sample (material); Optimization problem; Control (management); Action (physics); 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":[],"consensus_categories":[],"category_scores_codex":[0.00006448638,0.0001510556,0.0001319676,0.0001167094,0.0001557441,0.00008311152,0.0008241665,0.00003893689,0.000003397959],"category_scores_gemma":[0.00002318474,0.0001586154,0.00004859286,0.001087953,0.0000486341,0.000835464,0.0002121048,0.0002220484,0.00002640802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007737594,"about_ca_system_score_gemma":0.0001314868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001281496,"about_ca_topic_score_gemma":5.272802e-7,"domain_scores_codex":[0.9990225,0.00003412773,0.00009459595,0.0004362939,0.00007974777,0.0003326893],"domain_scores_gemma":[0.9992067,0.00005482761,0.00008565744,0.0003893312,0.00005141582,0.0002121343],"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":[0.0000244061,0.000005624837,0.002338035,0.000007363617,0.00001344008,0.0001147437,0.0002806548,0.9431092,0.000007541018,0.05395639,0.00003150092,0.0001110641],"study_design_scores_gemma":[0.000447014,0.0001238016,0.0001696401,0.00002585883,0.000009976005,9.601456e-7,0.0000448923,0.9986956,0.00005965003,0.00008199258,0.0001401655,0.0002005016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02220945,0.000004821209,0.9747429,0.0003639436,0.00004087388,0.00008043671,2.049984e-7,0.000330567,0.002226816],"genre_scores_gemma":[0.99066,0.000007087647,0.008249961,0.0008315867,0.00007331253,4.388145e-7,0.000001607825,0.00001395495,0.0001620812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9684505,"threshold_uncertainty_score":0.6468146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2271002738639286,"score_gpt":0.1933980817790889,"score_spread":0.03370219208483966,"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."}}