{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000166643,0.0002680115,0.0003391281,0.0003026182,0.0002587576,0.0001639617,0.0005924539,0.0002572096,0.000006872709],"category_scores_gemma":[0.0002161412,0.0002399544,0.00002319002,0.0009402892,0.0002928711,0.0001912767,0.0001516675,0.0008893973,0.00001638324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000272282,"about_ca_system_score_gemma":0.0001094128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005930837,"about_ca_topic_score_gemma":0.00001902354,"domain_scores_codex":[0.9982878,0.00007031995,0.0003972998,0.0006792534,0.0002240021,0.0003413327],"domain_scores_gemma":[0.9988444,0.0002108826,0.0002538235,0.0004453149,0.0001204679,0.0001250499],"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":[0.0005117355,0.00003499932,0.00245234,0.00005387887,0.0001041443,0.0000361778,0.001187964,0.5205735,0.002263315,0.4116777,0.0001151626,0.06098911],"study_design_scores_gemma":[0.004812123,0.001203458,0.001775125,0.00007145674,0.00003305276,0.00002305086,0.0003320757,0.9833694,0.0008890411,0.002915802,0.004118797,0.0004565937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004496803,0.00008858137,0.9784164,0.01345977,0.00003072223,0.0008429344,0.000004866547,0.0004093121,0.002250607],"genre_scores_gemma":[0.9927349,0.0001082864,0.005637289,0.001086385,0.00004967909,0.0002471947,0.00001513607,0.00001321371,0.0001079123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9882381,"threshold_uncertainty_score":0.9785056,"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."}}