{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001239134,0.0005268194,0.0004986811,0.0006130923,0.0006154754,0.00110574,0.001583165,0.0009852547,0.007906214],"category_scores_gemma":[0.01166209,0.0003470482,0.0005423318,0.0004416401,0.001626807,0.004153659,0.001895009,0.002491866,0.000572334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009130081,"about_ca_system_score_gemma":0.001623228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002837504,"about_ca_topic_score_gemma":0.004704736,"domain_scores_codex":[0.999087,0.0003150707,0.00006411429,0.0001799864,0.0002615874,0.00009239936],"domain_scores_gemma":[0.9962998,0.00225877,0.0002540067,0.0005768128,0.0003444022,0.0002662239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003795486,0.0001672671,0.001526754,0.0002253467,0.00003867359,0.0002816572,0.000429982,0.4130863,0.005018907,0.4522303,0.002959619,0.1236555],"study_design_scores_gemma":[0.00002957749,0.00006929943,0.000244143,0.00004074028,0.00001137831,0.00004838891,0.0000491273,0.7224932,0.00252295,0.2708384,0.003631957,0.00002075528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02591925,0.0001143984,0.9691713,0.0003027991,0.00005942979,0.00008656811,0.0001909351,0.0006459298,0.003509332],"genre_scores_gemma":[0.7254493,0.0001269628,0.2687194,0.0001906785,0.00003162815,0.0002866822,0.0003182024,0.0002091294,0.004668046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007906214,"threshold_uncertainty_score":0.02644897,"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."}}