{"id":"W7124164391","doi":"10.65109/pwam3332","title":"Smart exploration in reinforcement learning using absolute temporal difference errors","year":2013,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; State (computer science); Temporal difference learning; Function (biology); Control (management); Function approximation","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","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009309756,0.0006902455,0.0006255332,0.000671872,0.0005308934,0.00143597,0.001368804,0.0003036601,0.001259226],"category_scores_gemma":[0.0002511245,0.0007050827,0.0001419344,0.001398788,0.0001875909,0.004483411,0.001181029,0.001155161,0.001181996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006110258,"about_ca_system_score_gemma":0.0003658538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004401286,"about_ca_topic_score_gemma":0.00009788236,"domain_scores_codex":[0.9940043,0.0004128892,0.001800994,0.00108923,0.001253467,0.001439123],"domain_scores_gemma":[0.9972531,0.0001542383,0.0008304356,0.001061789,0.0003482307,0.0003522519],"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":[0.000008978982,0.00004393325,0.0168488,0.00006179991,0.00002737711,0.00001167919,0.003448415,0.9707837,0.001077019,0.002090172,0.00009309603,0.00550504],"study_design_scores_gemma":[0.0008123497,0.0005094639,0.01282309,0.0003244049,0.0000168914,0.000007780441,0.0006688234,0.9831087,0.0002722542,0.0002489056,0.0004014064,0.0008059216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09957088,0.00005572442,0.8918079,0.0007117892,0.001165432,0.001181555,1.058165e-7,0.0002039323,0.005302738],"genre_scores_gemma":[0.9509858,0.00009685748,0.02913741,0.0003142654,0.0001058572,0.00006285047,0.00001515806,0.00004863605,0.01923314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8626704,"threshold_uncertainty_score":0.9996538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06006734924730255,"score_gpt":0.2738622850019143,"score_spread":0.2137949357546117,"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."}}