{"id":"W1683981004","doi":"10.1109/acc.2015.7172192","title":"Reinforcement learning in decentralized stochastic control systems with partial history sharing","year":2015,"lang":"en","type":"article","venue":"","topic":"Age of Information Optimization","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Reinforcement; Control (management); 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":[0.0003825656,0.00008617458,0.0001201579,0.0001092432,0.00002865839,0.00009294343,0.0002774254,0.00002943501,0.00002203389],"category_scores_gemma":[0.00006127407,0.00007157818,0.00001191004,0.0001215831,0.0000150258,0.00102357,0.00005768764,0.00008631293,0.00004455534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005429094,"about_ca_system_score_gemma":0.000158786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001163092,"about_ca_topic_score_gemma":0.000007222092,"domain_scores_codex":[0.9990395,0.00003127324,0.0002773989,0.000143966,0.0003043708,0.0002034419],"domain_scores_gemma":[0.9994432,0.00002005132,0.0001328457,0.0001891452,0.00010732,0.0001074232],"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":[0.00002364209,0.000005455052,0.0004261267,0.000004345455,0.000004389302,0.000002729644,0.001218909,0.9810601,0.000001908898,0.01689939,0.0002204664,0.0001324855],"study_design_scores_gemma":[0.001886217,0.00007499537,0.00004600215,0.0000268713,0.000002254411,0.000007098747,0.0001203327,0.9963467,0.000005124284,0.000007241237,0.00137386,0.0001033361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001371496,0.00004994896,0.9917707,0.0000885519,0.0002233435,0.0002584838,2.911503e-8,0.0001830774,0.006054362],"genre_scores_gemma":[0.9914246,0.000001060471,0.007274736,0.0001350321,0.00001538117,0.0000338513,0.000003046423,0.000005069741,0.001107243],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9900531,"threshold_uncertainty_score":0.2918873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02266089938574876,"score_gpt":0.21526126131915,"score_spread":0.1926003619334012,"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."}}