{"id":"W2159849946","doi":"","title":"Universal Option Models","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Function (biology); Consistency (knowledge bases); Domain (mathematical analysis); Task (project management); Relevance (law); Preference; Construct (python library); Mathematical optimization; Computation; Mathematics; Artificial intelligence; Algorithm; Economics","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":[0.0001086811,0.00003971882,0.00003745064,0.00003533783,0.00003922236,0.00006346341,0.0003552014,0.00002048399,0.00001451076],"category_scores_gemma":[0.000008957973,0.00003566397,0.00001652758,0.00008632094,0.000009751057,0.0004941315,0.0001068583,0.00004219844,0.0001592591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001673807,"about_ca_system_score_gemma":0.000009360574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008342619,"about_ca_topic_score_gemma":3.518269e-7,"domain_scores_codex":[0.9995859,0.00002004559,0.00005820354,0.0001089022,0.0001251565,0.0001017738],"domain_scores_gemma":[0.999642,0.00002444636,0.00002170052,0.0002536426,0.00002513744,0.00003310282],"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":[1.33801e-7,9.545846e-7,0.000008932583,4.354426e-7,7.034853e-7,1.180437e-7,0.00003134576,0.5130403,0.0000197924,0.4851099,0.0001437839,0.001643547],"study_design_scores_gemma":[0.00008242006,0.0000308054,0.00005427653,0.000001627737,6.887912e-7,9.476649e-7,0.000004545911,0.989227,0.0001127618,0.006534628,0.003899739,0.00005057077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000289466,8.818433e-7,0.8667594,0.0002593936,0.0001113414,0.00002290156,8.753784e-9,0.0001712416,0.1323854],"genre_scores_gemma":[0.827216,0.00000161332,0.1672137,0.000218442,0.00002110662,4.133109e-7,4.478233e-7,0.000002311618,0.005325983],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8269265,"threshold_uncertainty_score":0.2047007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01502667130496796,"score_gpt":0.2061742516036106,"score_spread":0.1911475802986426,"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."}}