{"id":"W2165235114","doi":"","title":"Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task","year":2000,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Q-learning; Markov decision process; Computer science; Task (project management); Artificial intelligence; Markov chain; Sampling (signal processing); Markov process; Machine learning; State (computer science); Representation (politics); Gibbs sampling; Table (database); Action (physics); Algorithm; Data mining; Mathematics; Statistics; Engineering","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":[0.003969552,0.0009745232,0.001477511,0.0008210494,0.0005449431,0.001376951,0.001836503,0.001937747,0.002257761],"category_scores_gemma":[0.01325579,0.0008032052,0.000606782,0.0006970788,0.001970151,0.002724478,0.001390556,0.001777834,0.0003069513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001753666,"about_ca_system_score_gemma":0.001235997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005937122,"about_ca_topic_score_gemma":0.003655327,"domain_scores_codex":[0.9989082,0.0006799006,0.00004954195,0.0001637374,0.0001086875,0.00008999063],"domain_scores_gemma":[0.9918533,0.006786495,0.0004467581,0.0003376585,0.0003694894,0.000206411],"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":[0.00003584363,0.0000169928,0.0003201918,0.00001483363,0.00001404668,0.00002210091,0.0000291328,0.9844276,0.0001532852,0.00764507,0.0001417178,0.007179136],"study_design_scores_gemma":[0.000005381834,0.000009964012,0.00003586489,0.00000266075,0.00000186256,0.000003814967,0.000002496171,0.9913244,0.0000666647,0.008485475,0.00005810098,0.000003266963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03308357,0.0001610384,0.965246,0.0002627195,0.00002318028,0.00004341005,0.00003881297,0.0001963715,0.0009448888],"genre_scores_gemma":[0.8103815,0.0001713636,0.1872234,0.0001196893,0.00003461444,0.0002465653,0.0001052565,0.0000981615,0.001619517],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005937122,"threshold_uncertainty_score":0.02099323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03542532701238336,"score_gpt":0.293271296584887,"score_spread":0.2578459695725036,"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."}}