{"id":"W3132255199","doi":"","title":"C-Learning: Horizon-Aware Cumulative Accessibility Estimation","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","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; Motion planning; Time horizon; Generalization; Sample (material); Reliability (semiconductor); Set (abstract data type); Path (computing); Code (set theory); Field (mathematics); Machine learning; Artificial intelligence; Mathematical optimization; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003427083,0.0002178495,0.0001967795,0.0002212807,0.0004390505,0.0008983021,0.0009341544,0.00009922024,0.00087126],"category_scores_gemma":[0.002388351,0.0002366133,0.0001204312,0.0005405361,0.00008421201,0.001143502,0.0004310605,0.0008120502,0.0004120698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001764418,"about_ca_system_score_gemma":0.000317342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003204924,"about_ca_topic_score_gemma":0.000004784248,"domain_scores_codex":[0.9971392,0.0004064748,0.0004811007,0.0007566822,0.0009282992,0.0002882481],"domain_scores_gemma":[0.9972612,0.0005325531,0.00036736,0.0005558718,0.001159862,0.0001231929],"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":[0.00001091705,0.00006648419,0.009806041,0.000007143305,0.00006589598,0.00003526615,0.001522176,0.8531891,0.0004937368,0.1201723,0.0001879382,0.01444297],"study_design_scores_gemma":[0.0003772728,0.0001657994,0.01519111,0.00006286294,0.00000947195,0.00001680752,0.0006901455,0.9762689,0.001198488,0.004272874,0.001505577,0.0002407037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02022588,0.000006459585,0.8934277,0.003943509,0.000796554,0.0001563789,0.000002503164,0.0004289747,0.08101206],"genre_scores_gemma":[0.971356,0.00003110097,0.01215678,0.000113419,0.00009398664,0.00003976418,0.000210891,0.00001743597,0.01598058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9511302,"threshold_uncertainty_score":0.9648809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06374053049019669,"score_gpt":0.3772116194799136,"score_spread":0.3134710889897169,"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."}}