{"id":"W3110243076","doi":"10.48550/arxiv.2012.02051","title":"Reinforcement Learning in Decentralized Stochastic Control Systems with Partial History Sharing","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Age of Information Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Partially observable Markov decision process; Markov decision process; Benchmark (surveying); Decentralised system; Optimal control; Class (philosophy); Representation (politics); Information sharing; Mathematical optimization; Control (management); Markov process; Markov chain; Artificial intelligence; Markov model; Machine learning; Mathematics","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":[0.001693201,0.0006201927,0.001130061,0.0003040722,0.000551677,0.0008278345,0.001014151,0.0008946779,0.001526424],"category_scores_gemma":[0.005224466,0.0003605017,0.0004448385,0.0003731754,0.001613234,0.0009752714,0.00112091,0.001154688,0.0001404699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001570838,"about_ca_system_score_gemma":0.001411887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00935167,"about_ca_topic_score_gemma":0.004667918,"domain_scores_codex":[0.9989813,0.0003829782,0.00003692668,0.0002143673,0.000241474,0.0001429335],"domain_scores_gemma":[0.9972668,0.001775317,0.0003854102,0.000167471,0.0002774402,0.0001275304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003274137,0.0000169617,0.0002342782,0.00002170194,0.0000154695,0.00004955147,0.00003339758,0.9751641,0.0003714569,0.01936991,0.0001749811,0.004515468],"study_design_scores_gemma":[0.000008881322,0.00001125639,0.00004461597,0.000001559384,0.000001861287,0.000004368204,0.000003399615,0.9934927,0.00007720279,0.006248633,0.0001031121,0.000002319329],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06003776,0.0002309112,0.9352632,0.000466077,0.00004268825,0.00004957499,0.00005124349,0.0002450827,0.003613499],"genre_scores_gemma":[0.9768026,0.0000996299,0.02074181,0.00006421826,0.00002627695,0.00008773871,0.00003778316,0.00001945283,0.002120307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00935167,"threshold_uncertainty_score":0.0185945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05080245192887493,"score_gpt":0.1672835236424104,"score_spread":0.1164810717135355,"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."}}