{"id":"W2002256627","doi":"10.1109/adprl.2013.6614986","title":"Exponential moving average Q-learning algorithm","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Variety (cybernetics); Computer science; Q-learning; Exponential function; Algorithm; Policy learning; Markov decision process; State (computer science); Mathematical optimization; Matrix (chemical analysis); Artificial intelligence; Machine learning; Mathematics; Markov process","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":[0.002537178,0.0008191015,0.001767144,0.0006691878,0.0006814266,0.001099626,0.002371465,0.001566549,0.004654617],"category_scores_gemma":[0.006509158,0.0004490478,0.0005355998,0.0007714968,0.001043634,0.001258505,0.001538505,0.00166047,0.00112129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008904142,"about_ca_system_score_gemma":0.002299163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003839344,"about_ca_topic_score_gemma":0.002006974,"domain_scores_codex":[0.998584,0.0005469793,0.00007592537,0.0002911133,0.0003529701,0.0001489885],"domain_scores_gemma":[0.9975137,0.001353825,0.0001829923,0.0001625511,0.0006764848,0.0001105259],"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":[0.0001048253,0.0001167463,0.0007920532,0.000104514,0.00006750815,0.0000766817,0.00007423206,0.7893979,0.00106891,0.04300994,0.002836027,0.1623507],"study_design_scores_gemma":[0.00001776997,0.0000232494,0.00004223277,0.000004565051,0.000004976609,0.00001619693,0.000003370317,0.9935324,0.0002183859,0.005430853,0.0007018612,0.000004137365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002852254,0.0001968687,0.9948639,0.0001384439,0.00004154806,0.0000474826,0.0000147398,0.0001975159,0.001647235],"genre_scores_gemma":[0.4790668,0.0004746602,0.5099707,0.0004560291,0.000131863,0.0004896005,0.0001877902,0.0001110997,0.009111368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004654617,"threshold_uncertainty_score":0.01557124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007682844823853384,"score_gpt":0.2071727335532115,"score_spread":0.1994898887293581,"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."}}