{"id":"W4385430519","doi":"10.15607/rss.2023.xix.040","title":"SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering","year":2023,"lang":"en","type":"article","venue":"","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Rendering (computer graphics); Reinforcement learning; Differentiable function; Computer science; Artificial intelligence; Computer graphics (images); Mathematics; Mathematical analysis","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":[0.0008668103,0.0007985808,0.000973388,0.0002883281,0.0002839681,0.0008044159,0.001562918,0.000940516,0.002384618],"category_scores_gemma":[0.003727282,0.0004555077,0.000660892,0.0002103856,0.001003911,0.0008502667,0.001230509,0.001681199,0.0003608309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000762925,"about_ca_system_score_gemma":0.001231584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0040699,"about_ca_topic_score_gemma":0.003754627,"domain_scores_codex":[0.9996626,0.0001062307,0.00001625123,0.00006365304,0.000111913,0.00003937811],"domain_scores_gemma":[0.9987364,0.000768382,0.0001184828,0.0001587533,0.0001318713,0.0000860403],"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":[0.00003843475,0.00002600705,0.0002680507,0.00002411805,0.00001250834,0.00003446476,0.00002464906,0.979452,0.001398728,0.004498873,0.0003836505,0.01383837],"study_design_scores_gemma":[0.00000449175,0.00000626289,0.000009522074,9.947877e-7,0.000001033603,0.000003041143,8.040624e-7,0.998812,0.0002068308,0.0008703014,0.00008340706,0.000001369944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01172292,0.0000733537,0.9852163,0.0001507184,0.00002806511,0.0000359348,0.00002496734,0.001197563,0.001550214],"genre_scores_gemma":[0.7946514,0.0001058603,0.2026956,0.0001621443,0.00002668138,0.0001482162,0.00009420999,0.0002084662,0.001907322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0040699,"threshold_uncertainty_score":0.008092403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1599906926541879,"score_gpt":0.4130353987395262,"score_spread":0.2530447060853384,"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."}}