{"id":"W2169619645","doi":"10.5555/2484920.2485084","title":"Smart exploration in reinforcement learning using absolute temporal difference errors","year":2013,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; State (computer science); Function (biology); Artificial intelligence; Function approximation; Control (management); Machine learning; Algorithm; Artificial neural network","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":[0.0004013775,0.000326112,0.0003495043,0.0002562618,0.0002838597,0.000422989,0.0004722606,0.0001140976,0.00001898418],"category_scores_gemma":[0.00005351395,0.0002987753,0.00004944437,0.0003205286,0.00005872198,0.00142779,0.0004100343,0.0002925943,0.0001084446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001910326,"about_ca_system_score_gemma":0.00004879791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00421482,"about_ca_topic_score_gemma":0.00003224123,"domain_scores_codex":[0.9973987,0.0002485389,0.0006908059,0.000579794,0.0005194232,0.0005627802],"domain_scores_gemma":[0.9987924,0.00005292565,0.0004134124,0.0004035714,0.0001493699,0.0001883981],"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":[0.000006353057,0.00005383734,0.03842801,0.00005249882,0.00005739905,0.00001976851,0.003624791,0.9550254,0.0006567722,0.0008062542,0.0001252262,0.001143648],"study_design_scores_gemma":[0.0008635098,0.0001604327,0.0436471,0.0001924341,0.000008756949,0.000006031671,0.0007918809,0.9534333,0.00002698218,0.00001229365,0.0005362582,0.0003209717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1902142,0.00009192763,0.8075156,0.00004357572,0.0006564858,0.00103637,5.479687e-7,0.00009644435,0.0003449435],"genre_scores_gemma":[0.9886762,0.00006678287,0.007528981,0.00008723621,0.00003992909,0.00010097,0.00001331936,0.00002503665,0.003461479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7999865,"threshold_uncertainty_score":0.9999464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1078690293136804,"score_gpt":0.2926166985086204,"score_spread":0.18474766919494,"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."}}