{"id":"W2073549596","doi":"10.1109/icsmc.2012.6378016","title":"Acquiring a broad range of empirical knowledge in real time by temporal-difference learning","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generality; Robot; Computer science; Mobile robot; Set (abstract data type); Range (aeronautics); Artificial intelligence; Interface (matter); Robot learning; Human–computer interaction; Engineering","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":[0.002203222,0.0006788129,0.0007101569,0.0005242245,0.0003201276,0.0008767649,0.001749011,0.0008483871,0.001485687],"category_scores_gemma":[0.01253068,0.0004805347,0.0006283356,0.0005992728,0.001579868,0.003140129,0.001223748,0.001805234,0.0002922172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025641,"about_ca_system_score_gemma":0.0007196711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002696262,"about_ca_topic_score_gemma":0.002938096,"domain_scores_codex":[0.9991813,0.0002274187,0.00006259678,0.0002519537,0.0002304328,0.0000461341],"domain_scores_gemma":[0.993232,0.004766849,0.0004787934,0.00101939,0.0003827083,0.0001202459],"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":[0.0003033714,0.0002700174,0.003958397,0.0001598971,0.0001299364,0.0001818539,0.0002252423,0.6954923,0.01211941,0.04456473,0.001288966,0.2413058],"study_design_scores_gemma":[0.00001183093,0.00003240901,0.0004880362,0.000008825848,0.000005983075,0.00003048295,0.00001217538,0.9713274,0.002186976,0.02551804,0.000366602,0.00001117404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02975223,0.0001123866,0.9684419,0.0002261674,0.00001656334,0.00002015447,0.00005298511,0.0003151288,0.001062465],"genre_scores_gemma":[0.7824989,0.0002078609,0.2155788,0.0001768174,0.00004002047,0.00009539147,0.0002196909,0.00005933699,0.001123125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002696262,"threshold_uncertainty_score":0.01165193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03609110578036012,"score_gpt":0.3149373958607417,"score_spread":0.2788462900803815,"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."}}