{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00136441,0.001185677,0.001523263,0.001176615,0.0006032849,0.00112093,0.002760196,0.001570904,0.005999391],"category_scores_gemma":[0.008942839,0.0005939601,0.0008401045,0.0009341883,0.001180689,0.001937519,0.002448179,0.002578844,0.0009219241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001435161,"about_ca_system_score_gemma":0.0029892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01152087,"about_ca_topic_score_gemma":0.01314735,"domain_scores_codex":[0.9991186,0.0001857202,0.00004609963,0.0002370431,0.0002720238,0.0001405095],"domain_scores_gemma":[0.9955445,0.002769802,0.0003366297,0.0005164863,0.0005506285,0.0002820008],"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":[0.0001653035,0.0001110519,0.001051823,0.0001403465,0.00004390685,0.00007511966,0.00007619515,0.7847274,0.001650568,0.01235251,0.00442033,0.1951854],"study_design_scores_gemma":[0.00001254885,0.0000184543,0.0000658725,0.000008425112,0.000004449879,0.00001321153,0.000004977605,0.9919872,0.0005358824,0.00692613,0.0004175201,0.000005343176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00605212,0.0001583326,0.9905992,0.0001004279,0.00002706391,0.00005692477,0.00009830757,0.00172583,0.001181802],"genre_scores_gemma":[0.5669572,0.0002947022,0.4266716,0.0003136367,0.00009518163,0.000392812,0.0006985349,0.0007546592,0.003821778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01152087,"threshold_uncertainty_score":0.02290761,"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."}}