{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005995398,0.0001453622,0.0001838785,0.0002190252,0.0003975561,0.0002225049,0.0001515381,0.00006770554,0.0001506167],"category_scores_gemma":[0.0001705743,0.0001218048,0.00007606769,0.0008851885,0.00004250091,0.0001751985,0.00008244017,0.0001145706,0.00008566293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003809528,"about_ca_system_score_gemma":0.00003923544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003049572,"about_ca_topic_score_gemma":0.000005361231,"domain_scores_codex":[0.9981573,0.00005100467,0.0004348724,0.0004263656,0.000703208,0.0002272631],"domain_scores_gemma":[0.998296,0.0007960297,0.0001640568,0.0004177789,0.0002374937,0.00008867373],"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":[0.000007282741,0.000008220021,0.0007108369,0.000004532069,0.000002717688,2.706909e-7,0.00004591463,0.974485,0.00110457,0.0004755837,0.0002517165,0.02290331],"study_design_scores_gemma":[0.0002802895,0.00002602881,0.0006130818,0.00001302885,0.000007621682,9.171459e-8,0.00006592026,0.9817163,0.004598938,0.01146771,0.001059306,0.000151662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05496044,0.0000023121,0.9429484,0.0003031125,0.00002205026,0.0002464855,0.000001963961,0.0005672482,0.0009480069],"genre_scores_gemma":[0.9911702,0.000001033486,0.005522784,0.0002108839,0.00003258025,0.00001409123,0.00005248984,0.00001923915,0.002976706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9374256,"threshold_uncertainty_score":0.4967056,"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."}}