{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00267182,0.0008363477,0.001090683,0.0004913798,0.0002598131,0.0008652832,0.001136006,0.0008724785,0.001126698],"category_scores_gemma":[0.01099616,0.0004401472,0.0004023465,0.0004128853,0.001687813,0.002105606,0.001579434,0.001468629,0.0001498979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000839858,"about_ca_system_score_gemma":0.0008503809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001888809,"about_ca_topic_score_gemma":0.001291005,"domain_scores_codex":[0.9990011,0.0004198154,0.00006219536,0.0001634942,0.0002745318,0.00007900253],"domain_scores_gemma":[0.9944174,0.004257329,0.0004510807,0.0003098468,0.0003486084,0.0002157671],"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":[0.0001860042,0.00005027924,0.0008560445,0.00007903602,0.00003642451,0.00005478567,0.00007836601,0.9210731,0.00208744,0.0361036,0.000263568,0.03913136],"study_design_scores_gemma":[0.00001240527,0.00002728714,0.00004724197,0.000003580048,0.00000242637,0.000006245525,0.000001846512,0.9915758,0.0003911631,0.007850587,0.00007809643,0.000003309185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03218501,0.0002343137,0.9663579,0.0001174925,0.00002877618,0.00002402151,0.00001238257,0.0001889278,0.0008513137],"genre_scores_gemma":[0.8937624,0.0001601774,0.1044625,0.00006288031,0.00003526307,0.0001073865,0.00003568197,0.00007158906,0.001302137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00267182,"threshold_uncertainty_score":0.01413012,"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."}}