{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006072391,0.0001578987,0.0002610106,0.000145284,0.00005524982,0.00005033233,0.0006611092,0.00009583135,0.00008863515],"category_scores_gemma":[0.00009806894,0.0001409734,0.00005420368,0.0004700843,0.00005941056,0.0004754236,0.000428144,0.0002538243,0.0002671576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007122145,"about_ca_system_score_gemma":0.00004713416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009343362,"about_ca_topic_score_gemma":0.000003137814,"domain_scores_codex":[0.9984328,0.0001704017,0.00038971,0.000247309,0.0002755515,0.0004842643],"domain_scores_gemma":[0.9990985,0.000234583,0.0001388702,0.0003465499,0.0000514276,0.0001300199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001117402,0.0001783901,0.9668031,0.00004929042,0.00001589129,0.00000230171,0.005271791,0.009023541,0.006828182,0.001552706,0.00232488,0.007938761],"study_design_scores_gemma":[0.0009548209,0.0002382216,0.1595374,0.0001059128,0.000007423093,0.000007945555,0.0001141772,0.8315058,0.002566717,0.00002985141,0.004451754,0.0004799392],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3786589,0.0001826016,0.5777215,0.000123665,0.0001620712,0.000170505,2.711407e-7,0.0002600825,0.04272047],"genre_scores_gemma":[0.9744076,0.00001787223,0.01298105,0.00003695552,0.00003970508,0.000006217104,0.000002888875,0.0000119672,0.01249575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8224823,"threshold_uncertainty_score":0.5748727,"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."}}