{"id":"W7132865739","doi":"","title":"Constrained, Curiosity-driven Trajectory Optimization for Learned Quadrotor Control","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Trajectory; Stability (learning theory); Probabilistic logic; Reinforcement learning; Control theory (sociology); Robot; Control (management); Model predictive control; Optimal control; State space","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","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001002167,0.0009680149,0.001134174,0.0005810402,0.001500198,0.0007303504,0.002120096,0.0005916195,0.003463192],"category_scores_gemma":[0.0007767925,0.001208641,0.0006592827,0.0008157523,0.0001952522,0.0005781666,0.0001997686,0.0013421,0.00007165825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005691941,"about_ca_system_score_gemma":0.001452307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009838893,"about_ca_topic_score_gemma":0.0000226702,"domain_scores_codex":[0.9940699,0.0006153983,0.001196658,0.001608657,0.001355588,0.001153854],"domain_scores_gemma":[0.9947699,0.001096678,0.001811549,0.001275179,0.0007017016,0.0003450465],"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":[0.0004259628,0.0001190601,0.00007203197,0.0005506091,0.0002968709,0.00001909029,0.0129923,0.9783558,0.0004682107,0.004105631,0.0006847284,0.001909655],"study_design_scores_gemma":[0.004242662,0.001367683,0.0000649236,0.0002337071,0.0003306275,0.00001647431,0.00449304,0.976377,0.0001804168,0.00002234594,0.0115051,0.001166069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007641807,0.0004976045,0.9841719,0.0009186748,0.004190091,0.005307594,0.00004043649,0.0003798309,0.003729726],"genre_scores_gemma":[0.4486345,0.002057743,0.3552854,0.002793077,0.001844827,0.005162201,0.006826913,0.0008758913,0.1765194],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6288865,"threshold_uncertainty_score":0.9997997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02915650439830587,"score_gpt":0.3380137081547251,"score_spread":0.3088572037564193,"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."}}