{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001625338,0.0001250573,0.0001094163,0.00009083295,0.0001803632,0.0005147482,0.0007013982,0.00005130532,0.001018931],"category_scores_gemma":[0.00005406539,0.000113916,0.00005552598,0.0002029228,0.00002152217,0.001014519,0.0004454528,0.0002443581,0.00237393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003256714,"about_ca_system_score_gemma":0.00001956185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001046084,"about_ca_topic_score_gemma":1.963609e-7,"domain_scores_codex":[0.9987599,0.00005892874,0.0002113326,0.0002785411,0.0003351056,0.0003562091],"domain_scores_gemma":[0.9992983,0.00007414232,0.0000770074,0.0003724648,0.0000741506,0.0001039645],"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":[5.043788e-7,0.00002408687,0.0012763,0.00001059055,0.00003253487,0.00001926675,0.0009230383,0.7024409,0.002333808,0.0167682,0.00387778,0.272293],"study_design_scores_gemma":[0.0001479945,0.00004610051,0.001121216,0.000006794403,0.000001308233,0.00000784958,0.0000315952,0.9936446,0.0007316298,0.0002013181,0.003898399,0.0001612091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001439828,0.000009725381,0.9703557,0.0002119916,0.000379267,0.0001296722,3.449936e-8,0.000496723,0.02697708],"genre_scores_gemma":[0.5143682,0.000007075883,0.4629816,0.0003564323,0.0001165101,0.00001692753,0.000002605961,0.00001431904,0.02213628],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5129284,"threshold_uncertainty_score":0.9998943,"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."}}