{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001845115,0.0006493318,0.001234451,0.0003222973,0.0005401138,0.0008220479,0.001050289,0.0009071714,0.001398839],"category_scores_gemma":[0.005263872,0.0003829925,0.000462158,0.0003775326,0.00162893,0.0009310672,0.001130471,0.00112436,0.0001299245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001540858,"about_ca_system_score_gemma":0.001389435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008796854,"about_ca_topic_score_gemma":0.004391672,"domain_scores_codex":[0.9989139,0.0004097722,0.00003984583,0.000230249,0.0002534922,0.0001526832],"domain_scores_gemma":[0.9971672,0.001805053,0.0004365585,0.0001632193,0.0002940813,0.0001338793],"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":[0.00002953107,0.00001613236,0.0002174508,0.00002018199,0.00001528964,0.00004757738,0.00003018774,0.9798839,0.0003470344,0.01551733,0.0001378625,0.003737463],"study_design_scores_gemma":[0.000008735938,0.00001188391,0.00004344886,0.000001506105,0.000001902637,0.000004274048,0.000003272064,0.9948249,0.00007134319,0.004938737,0.00008773823,0.00000226643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05801883,0.0002268709,0.9377707,0.0003985762,0.00003924157,0.00005047668,0.00004532202,0.0002135772,0.003236428],"genre_scores_gemma":[0.9779298,0.00009740789,0.01979675,0.00006162563,0.00002448261,0.0000929618,0.00003538781,0.00001765471,0.001943828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008796854,"threshold_uncertainty_score":0.01749128,"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."}}