{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002137095,0.0002452853,0.0003250135,0.0002485937,0.00007506467,0.0001209829,0.0009914113,0.0001449276,0.000026692],"category_scores_gemma":[0.00004756203,0.0002778129,0.0000671462,0.0002863125,0.0000459584,0.0007263454,0.0006392045,0.000540764,0.00004299839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001232985,"about_ca_system_score_gemma":0.0003260006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001631886,"about_ca_topic_score_gemma":0.000009768573,"domain_scores_codex":[0.9985251,0.00008983732,0.0003191334,0.0006126781,0.0001498929,0.0003033128],"domain_scores_gemma":[0.9987189,0.00004435003,0.0004701686,0.0004904354,0.0001238285,0.0001522991],"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":[0.00007945723,0.00001083078,0.0006646968,0.00006328458,0.00003786173,0.00009015784,0.0007388548,0.9541873,0.000001962669,0.04405997,0.00004148848,0.00002415554],"study_design_scores_gemma":[0.001540935,0.00005811302,0.0001074287,0.0001779631,0.00002998595,0.000002785604,0.00007779172,0.9973025,0.000002146978,0.0001282326,0.0002735472,0.0002986149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00858407,0.00004297024,0.9889448,0.0000691289,0.0003792164,0.000547751,7.706851e-7,0.0002868313,0.001144517],"genre_scores_gemma":[0.9984658,0.00002382932,0.0008758982,0.0000837577,0.00002791546,0.000004364645,0.0000216976,0.00001360445,0.000483136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9898818,"threshold_uncertainty_score":0.9999674,"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."}}