{"id":"W3090693621","doi":"10.1109/ccta41146.2020.9206397","title":"Reinforcement Learning in Deep Structured Teams: Initial Results with Finite and Infinite Valued Features","year":2020,"lang":"en","type":"article","venue":"2020 IEEE Conference on Control Technology and Applications (CCTA)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain; Convergence (economics); Variable-order Markov model; Linear model; Quadratic equation; Linear regression; Orthonormal basis; Reinforcement learning; State (computer science)","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":[0.003691694,0.001527073,0.001864068,0.0006507582,0.0007209349,0.001353107,0.001800349,0.002146916,0.003390762],"category_scores_gemma":[0.01767635,0.0008070786,0.001362499,0.0007162205,0.002666396,0.003393581,0.002211167,0.004052427,0.0004769946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002048454,"about_ca_system_score_gemma":0.001174494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00512905,"about_ca_topic_score_gemma":0.002760844,"domain_scores_codex":[0.9988967,0.0005036733,0.00005041646,0.0002248415,0.0001831067,0.0001412158],"domain_scores_gemma":[0.9903148,0.007693896,0.0004392008,0.0003775874,0.0007539648,0.0004204955],"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":[0.0001490287,0.0001397095,0.0009189272,0.0003014345,0.00008665479,0.0001280963,0.0002484372,0.7071021,0.0007836237,0.2609474,0.001908896,0.02728577],"study_design_scores_gemma":[0.00001219641,0.00003616649,0.00006946175,0.00001869682,0.00000998997,0.00001089367,0.00001439866,0.9384249,0.0001360149,0.0608041,0.0004559775,0.00000713118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02629694,0.002938739,0.9618707,0.001126511,0.0001465507,0.00004587149,0.00006680197,0.0001650408,0.007342841],"genre_scores_gemma":[0.8808637,0.003885717,0.104861,0.0004215621,0.0003807554,0.0002206141,0.0002015455,0.0001445122,0.00902068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00512905,"threshold_uncertainty_score":0.01952374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01247933795613967,"score_gpt":0.244423156842766,"score_spread":0.2319438188866263,"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."}}