{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001586174,0.001241209,0.001561463,0.00119384,0.0006319107,0.001103592,0.002764308,0.001539714,0.005794253],"category_scores_gemma":[0.0100448,0.0006171521,0.0008248979,0.0009083503,0.001320094,0.001778734,0.002421022,0.002633998,0.0009060696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001492481,"about_ca_system_score_gemma":0.003154555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01138609,"about_ca_topic_score_gemma":0.01232951,"domain_scores_codex":[0.9990053,0.0002287398,0.00005212352,0.000270467,0.0002960437,0.0001473677],"domain_scores_gemma":[0.9944251,0.003614022,0.0003939757,0.0005925141,0.0006358862,0.0003386109],"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":[0.0001538693,0.00009407492,0.001047871,0.0001276212,0.00004277681,0.00006782984,0.00006543381,0.8346398,0.001356453,0.01153152,0.003637223,0.1472355],"study_design_scores_gemma":[0.0000125349,0.00001694451,0.00006773358,0.000007879185,0.000004012258,0.0000113396,0.00000397678,0.991946,0.0004781909,0.007072027,0.0003743923,0.000005050393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005943032,0.0001539991,0.9908976,0.0001058219,0.00002721843,0.00005595934,0.00008903532,0.001549468,0.00117778],"genre_scores_gemma":[0.5846868,0.000283305,0.4091682,0.0003003549,0.0001015741,0.000405046,0.0006096557,0.0007192705,0.003725715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01138609,"threshold_uncertainty_score":0.02263963,"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."}}