{"id":"W2808315817","doi":"10.65109/ntef7045","title":"Eligibility Traces for Options","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Backup; Reinforcement learning; Abstraction; Sampling (signal processing); Tree (set theory); Machine learning; Database","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":[0.0002186496,0.00004657885,0.00005004041,0.00002714421,0.0001250709,0.00009503324,0.0004243777,0.00002303196,0.00005177609],"category_scores_gemma":[0.00007947283,0.00003872625,0.00003354401,0.0001126427,0.00004981094,0.0002416581,0.00007488589,0.00002853871,0.0001545428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001375087,"about_ca_system_score_gemma":0.00002469036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005216685,"about_ca_topic_score_gemma":0.000004563726,"domain_scores_codex":[0.999474,0.00001102847,0.0001079872,0.0001694421,0.00009395602,0.0001435894],"domain_scores_gemma":[0.99938,0.00008123259,0.00002818078,0.0003709857,0.0001035264,0.00003609166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000479559,0.00003811213,0.001152267,0.00001429341,0.00001662347,2.713753e-7,0.0005780033,0.03165552,0.0006940553,0.9343499,0.01661696,0.01487919],"study_design_scores_gemma":[0.0001486076,0.0002091793,0.001551053,0.000003489622,0.000002352293,0.000001317006,0.00001276928,0.9483573,0.003190149,0.005111583,0.0413173,0.00009484858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001721116,0.000007347782,0.980527,0.0007677796,0.0002725358,0.0001367182,2.531624e-7,0.0001876047,0.01637969],"genre_scores_gemma":[0.4933819,0.000002761111,0.5016931,0.0003059102,0.0001043253,0.00001266099,7.964735e-7,0.000002988925,0.004495546],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9292383,"threshold_uncertainty_score":0.1986387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0352984014728696,"score_gpt":0.33755489885715,"score_spread":0.3022564973842803,"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."}}