{"id":"W2971273232","doi":"10.13140/rg.2.2.12370.50882","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Cumulant; Reinforcement learning; Computer science; Premise; Artificial intelligence; Machine learning; Formalism (music); Transfer of learning; Human–computer interaction; 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":[0.001871298,0.0006600809,0.0005961992,0.0004821176,0.0004845042,0.001109999,0.001306313,0.001024938,0.004216657],"category_scores_gemma":[0.005737448,0.0003858618,0.000751576,0.0004735253,0.00292804,0.003034458,0.0021468,0.001702464,0.0004328809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006467643,"about_ca_system_score_gemma":0.0006443114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001042132,"about_ca_topic_score_gemma":0.0009394205,"domain_scores_codex":[0.9990618,0.0004813572,0.00004097013,0.0001622754,0.0001760685,0.00007766992],"domain_scores_gemma":[0.9984162,0.000980119,0.0001264844,0.0002155744,0.0001019548,0.0001595943],"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":[0.0003405144,0.0001870814,0.001633565,0.0001732458,0.00007552438,0.0003263701,0.000556198,0.3645539,0.01251852,0.4674414,0.001213544,0.1509802],"study_design_scores_gemma":[0.00004926792,0.0001681531,0.0002340603,0.00003292092,0.00001574142,0.00006543199,0.00003514719,0.7025837,0.002471873,0.2917365,0.00258043,0.00002683601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01760693,0.00008077837,0.979336,0.0001736332,0.00002206364,0.00004051852,0.00002131213,0.0002344846,0.002484252],"genre_scores_gemma":[0.5806797,0.0001533945,0.4157253,0.0001410019,0.00003796086,0.0002428173,0.00004769858,0.00008963139,0.002882534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004216657,"threshold_uncertainty_score":0.01410615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0226661243442616,"score_gpt":0.172291409485245,"score_spread":0.1496252851409834,"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."}}