{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003967432,0.001891181,0.002269852,0.001474345,0.0007348809,0.003112921,0.004109584,0.003191912,0.01191082],"category_scores_gemma":[0.01796199,0.001220537,0.002299822,0.001592607,0.002431242,0.006231976,0.002718434,0.004159156,0.001051709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002461545,"about_ca_system_score_gemma":0.001629974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00531496,"about_ca_topic_score_gemma":0.005568335,"domain_scores_codex":[0.9971488,0.001166087,0.0001656107,0.0007657148,0.0004325536,0.0003212199],"domain_scores_gemma":[0.9896201,0.007782902,0.0009292267,0.0006725261,0.0004777437,0.0005173549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001014666,0.00006778157,0.001066939,0.0001308889,0.00008782269,0.0001674113,0.0001098824,0.7403853,0.0002917637,0.2383366,0.001442165,0.017812],"study_design_scores_gemma":[0.00001475895,0.00002797705,0.00006157592,0.00001532117,0.00001015443,0.00002342659,0.00001101953,0.8641845,0.00009339605,0.1346999,0.0008474496,0.000010575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01685037,0.0005334047,0.9769594,0.0006593491,0.00007160317,0.00008541188,0.0004692912,0.0004204048,0.003950694],"genre_scores_gemma":[0.6839913,0.0008471473,0.301525,0.0004773182,0.0001762636,0.0006662253,0.0009924199,0.0002005438,0.01112372],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01191082,"threshold_uncertainty_score":0.03984571,"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."}}