{"id":"W4302917494","doi":"10.48550/arxiv.1806.06161","title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement\\n Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Toyota Research Institute","keywords":"Reinforcement learning; Computer science; Leverage (statistics); Bottleneck; Reachability; Prior probability; Flexibility (engineering); Artificial intelligence; Optimal control; Curriculum; Mathematical optimization; Machine learning; Bayesian probability; Theoretical computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008842887,0.0007863097,0.0006509043,0.00040737,0.000436702,0.0004754129,0.00188571,0.00116524,0.007442932],"category_scores_gemma":[0.004197825,0.0004118644,0.0004046684,0.0002622143,0.0009261395,0.001139721,0.001987546,0.002101425,0.001000662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056499,"about_ca_system_score_gemma":0.001932644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003942973,"about_ca_topic_score_gemma":0.004607383,"domain_scores_codex":[0.9996378,0.00009268567,0.00001378183,0.00007809725,0.0001255637,0.00005192059],"domain_scores_gemma":[0.9991549,0.000454087,0.00007548773,0.000105599,0.0001245192,0.0000853876],"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":[0.00009587919,0.000143261,0.0004426204,0.0001290663,0.00001394288,0.00005569893,0.00008529331,0.8600625,0.003126321,0.04798127,0.003043629,0.08482053],"study_design_scores_gemma":[0.00001049777,0.00002525193,0.00002687975,0.000006566343,0.000001488199,0.000006534009,0.000002590756,0.9940233,0.0005015488,0.00464603,0.0007461699,0.000003254614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01288518,0.0001171319,0.9807146,0.0001934187,0.00004177264,0.00008720125,0.00006795472,0.00157168,0.004321036],"genre_scores_gemma":[0.5754963,0.0001961224,0.4161887,0.0003345295,0.00004406108,0.0006639454,0.0003998398,0.0003980199,0.006278452],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007442932,"threshold_uncertainty_score":0.02489907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06339507954544266,"score_gpt":0.2106728572109922,"score_spread":0.1472777776655496,"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."}}