{"id":"W3108136459","doi":"10.48550/arxiv.2011.12363","title":"C-Learning: Horizon-Aware Cumulative Accessibility Estimation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reachability; Reinforcement learning; Computer science; Time horizon; Generalization; Motion planning; Sample (material); Reliability (semiconductor); Set (abstract data type); Path (computing); Horizon; Code (set theory); Monotonic function; Machine learning; Mathematical optimization; Artificial intelligence; Robot; Theoretical computer science; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0003169673,0.0004239655,0.0004322068,0.0002052959,0.0002768781,0.0003509566,0.002585639,0.0003591596,0.00005129537],"category_scores_gemma":[0.0003154771,0.000506621,0.0002388747,0.0008271331,0.0001240871,0.0008779867,0.004028216,0.001482057,0.0002692755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004060979,"about_ca_system_score_gemma":0.0003286168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005637703,"about_ca_topic_score_gemma":0.000002647844,"domain_scores_codex":[0.9971654,0.0003356848,0.0003439317,0.001529812,0.0002262167,0.0003989119],"domain_scores_gemma":[0.997337,0.0002231008,0.0006287542,0.001290376,0.0002706499,0.0002500883],"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":[0.00001667121,0.00002270177,0.003124472,0.0001002644,0.00006577199,0.00009481475,0.0004588614,0.9686483,0.000005469083,0.02642587,0.0001209621,0.0009158686],"study_design_scores_gemma":[0.0003109514,0.0001897844,0.002622023,0.00007909796,0.0000537461,0.000001139569,0.00007158538,0.9810181,0.00005803748,0.01490556,0.0002088227,0.0004811459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03734597,0.000008428484,0.9572458,0.0002230423,0.0005662534,0.0004061655,0.000003536112,0.0007836184,0.003417145],"genre_scores_gemma":[0.9906147,0.00003058694,0.007689417,0.00006072491,0.00007448796,0.0000012024,0.00006293448,0.00002566947,0.001440303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9532687,"threshold_uncertainty_score":0.9997385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09698605659490178,"score_gpt":0.2335412704894695,"score_spread":0.1365552138945677,"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."}}