{"id":"W4212802944","doi":"10.3390/s22041393","title":"Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor Representation","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Reinforcement learning; Overfitting; Computer science; Kalman filter; Artificial intelligence; Temporal difference learning; Representation (politics); Inefficiency; Machine learning; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003275116,0.0001837068,0.000183164,0.0001559678,0.00064262,0.0001286373,0.0004888688,0.00003304328,0.00005687297],"category_scores_gemma":[0.00007292825,0.0001914125,0.00005421236,0.0003576913,0.00006162627,0.0002178115,0.0008904682,0.0004173382,0.00002299863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001408557,"about_ca_system_score_gemma":0.00003376918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002526695,"about_ca_topic_score_gemma":0.000006214391,"domain_scores_codex":[0.9979381,0.0002791157,0.0003307087,0.0004952876,0.0006121393,0.0003446324],"domain_scores_gemma":[0.9990394,0.0001096777,0.0002624429,0.0004167815,0.0000616863,0.0001100879],"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":[0.00001582588,0.00001748024,0.01178051,0.000007409337,0.0000228573,0.00002641863,0.002627145,0.9815009,0.0007866247,0.0009282234,0.0000386543,0.002247903],"study_design_scores_gemma":[0.0005020246,0.0003280204,0.01462885,0.000007882978,0.000008568915,0.00002124332,0.0006501584,0.9820635,0.0004716957,0.0000436399,0.001045711,0.0002286937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2040055,0.0000344258,0.7942806,0.0002673711,0.0003157296,0.0003276461,5.470212e-7,0.0001984424,0.000569627],"genre_scores_gemma":[0.9762602,0.00001465518,0.01650893,0.0001235503,0.00002756081,0.00003708642,0.00001607587,0.00001554294,0.006996397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7777718,"threshold_uncertainty_score":0.7805576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03640443974414519,"score_gpt":0.2723738731078577,"score_spread":0.2359694333637125,"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."}}