{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004711342,0.0002246985,0.0002322167,0.0002779739,0.0001697676,0.0002654998,0.00126984,0.00006329607,0.0004913087],"category_scores_gemma":[0.0001986226,0.000213372,0.00007693809,0.0006346844,0.00003212317,0.0005153877,0.0007772203,0.0002437187,0.0002328577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002055815,"about_ca_system_score_gemma":0.00006138317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009585436,"about_ca_topic_score_gemma":0.00002492927,"domain_scores_codex":[0.9975814,0.0001217285,0.0005309973,0.0005521345,0.0006329097,0.0005808025],"domain_scores_gemma":[0.9984858,0.00009356807,0.00008380191,0.001122595,0.00005565708,0.0001585763],"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":[0.000008731976,0.00001650556,0.001063746,0.000007055649,0.00001212199,0.00002302477,0.001821774,0.9880843,0.0009817386,0.002032791,0.0005087393,0.00543953],"study_design_scores_gemma":[0.0004567797,0.0001298732,0.0008915282,0.000058145,0.00000394332,0.000006817335,0.0001265917,0.9876698,0.002206798,0.00009568056,0.008069373,0.0002846359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07346973,0.00003453947,0.9013764,0.0004249245,0.0001625849,0.0003278399,9.788562e-8,0.0002933092,0.02391057],"genre_scores_gemma":[0.8093965,0.00004207529,0.1678926,0.0006181944,0.00006273037,0.0000243985,0.000002283021,0.00002044931,0.02194072],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7359268,"threshold_uncertainty_score":0.8701056,"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."}}