{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004918929,0.000140559,0.0001349159,0.0001423555,0.0002481855,0.0001417494,0.0009841279,0.00006655777,0.00002433511],"category_scores_gemma":[0.00006045204,0.0001315741,0.00005712131,0.000671623,0.00005067533,0.0006293,0.0004251398,0.0003648065,0.0005201855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001842347,"about_ca_system_score_gemma":0.00004936534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003308531,"about_ca_topic_score_gemma":0.000005957895,"domain_scores_codex":[0.9987655,0.0001251111,0.0001967672,0.0003891906,0.0001321841,0.000391245],"domain_scores_gemma":[0.9988744,0.0002512959,0.000164878,0.0005827343,0.000059593,0.00006710669],"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":[0.000006972976,0.000008116836,0.01513571,0.000004098441,0.000009231213,0.00001496538,0.0001840868,0.7817218,0.00005698203,0.2024894,0.00001594389,0.0003526672],"study_design_scores_gemma":[0.0006537866,0.0001452381,0.004271001,0.00003491904,0.000004372494,0.000001739617,0.0001897874,0.9908598,0.00006133061,0.0005795846,0.003025069,0.0001733899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3013898,0.000008497666,0.688684,0.00006801392,0.0003047718,0.0001891549,2.880584e-8,0.0001109095,0.009244878],"genre_scores_gemma":[0.9766018,0.00006507591,0.0003858418,0.00006885026,0.00001225043,4.718121e-7,0.000002017134,0.000008774814,0.02285491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6882982,"threshold_uncertainty_score":0.6686105,"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."}}