{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006362795,0.0007184686,0.0006601549,0.0002534597,0.0002580359,0.0005799416,0.0007344041,0.0005750325,0.002175803],"category_scores_gemma":[0.002262038,0.0003252469,0.000345969,0.0002237607,0.001027705,0.0005651205,0.001057647,0.0009417618,0.0001936074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008096093,"about_ca_system_score_gemma":0.0009347109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004053841,"about_ca_topic_score_gemma":0.002868854,"domain_scores_codex":[0.9998121,0.00005719325,0.000007559174,0.0000402401,0.0000514604,0.00003152739],"domain_scores_gemma":[0.9991688,0.000513254,0.00009821265,0.00004702485,0.0001149842,0.00005773663],"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":[0.00002243176,0.00001290835,0.0001488008,0.00002833213,0.000009853004,0.00002186811,0.00003138103,0.9855258,0.0007954313,0.007319608,0.0002296699,0.005853908],"study_design_scores_gemma":[0.000005150634,0.00001222291,0.00002199379,0.000003186019,9.335417e-7,0.000002189301,0.000003301767,0.9972801,0.0001266305,0.002420088,0.0001229099,0.000001213805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03084832,0.0001421083,0.9653208,0.0002397776,0.00002552613,0.0000348142,0.00003031739,0.0001877732,0.003170562],"genre_scores_gemma":[0.9221166,0.0001297158,0.07385998,0.0001136156,0.00002077077,0.0001659533,0.00007657382,0.00008559732,0.003431166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004053841,"threshold_uncertainty_score":0.008060455,"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."}}