{"id":"W75140964","doi":"","title":"Agnostic KWIK learning and efficient approximate reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Simple (philosophy); Artificial intelligence; Algorithm; Theoretical computer science; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002137746,0.0005079146,0.0004441837,0.0003673394,0.0008935704,0.0003867545,0.0009923064,0.0001876343,0.0004618417],"category_scores_gemma":[0.001778601,0.0004852816,0.00011214,0.0003967939,0.000298376,0.0003218936,0.0008197119,0.001859389,0.0005078994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009725716,"about_ca_system_score_gemma":0.0001195574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001257768,"about_ca_topic_score_gemma":2.896284e-7,"domain_scores_codex":[0.9961591,0.0007645282,0.0005711328,0.0009290642,0.0006612925,0.0009148603],"domain_scores_gemma":[0.9976578,0.0007568022,0.0005013457,0.0005801079,0.0002041431,0.0002997851],"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":[0.00006105223,0.00003428849,0.001532278,0.00004390314,0.00003994525,0.00002981481,0.005943616,0.6265475,0.0002945875,0.350251,0.00001019354,0.01521183],"study_design_scores_gemma":[0.0007592156,0.001352654,0.001037126,0.0003110425,0.00003470396,0.00003033787,0.001158852,0.9881581,0.0008118877,0.002992502,0.002625288,0.0007282777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01701988,0.00009492735,0.8758206,0.000076507,0.0003110179,0.0003280215,9.822605e-8,0.0008972455,0.1054517],"genre_scores_gemma":[0.981714,0.0001902386,0.005675476,0.0001280372,0.00005254315,0.00004115337,0.000008373858,0.00005470215,0.01213555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.964694,"threshold_uncertainty_score":0.9997599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03446888166875992,"score_gpt":0.247999907469349,"score_spread":0.2135310258005891,"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."}}