{"id":"W2970912723","doi":"","title":"Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Gossip; Asynchronous communication; Computer science; Reinforcement learning; Scalability; Distributed computing; Synchronization (alternating current); Gossip protocol; Artificial intelligence; Computer network","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":[0.0009806219,0.0006435915,0.0006437381,0.0002154577,0.0004401279,0.0005712343,0.001265755,0.0007707194,0.002002971],"category_scores_gemma":[0.002533945,0.0002928059,0.0003161619,0.0002102897,0.001003161,0.0007755255,0.001141004,0.00142136,0.0003906213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007449204,"about_ca_system_score_gemma":0.0008724623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002190477,"about_ca_topic_score_gemma":0.003198362,"domain_scores_codex":[0.9996332,0.0001401637,0.00001871036,0.00007715951,0.00008029474,0.00005040381],"domain_scores_gemma":[0.9989997,0.0005684245,0.0001050311,0.0001161927,0.0001260476,0.00008471731],"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":[0.0001097729,0.00003673531,0.0003907093,0.00003883298,0.00003269606,0.00004697496,0.00005403325,0.9618142,0.002555578,0.01572605,0.0007166102,0.01847779],"study_design_scores_gemma":[0.000006386582,0.00001659791,0.00002109345,0.000001393387,0.00000222377,0.000003479339,0.000002783949,0.9955213,0.00035167,0.003851643,0.0002193494,0.000002121934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03846586,0.000220515,0.9572396,0.0002583336,0.00006331276,0.00004197756,0.0000397306,0.0007040928,0.002966635],"genre_scores_gemma":[0.9262322,0.0001327938,0.0703412,0.0001012404,0.00003299144,0.0001172478,0.0000619987,0.00006738565,0.002912848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002190477,"threshold_uncertainty_score":0.006700635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03552543995273192,"score_gpt":0.1842428855091696,"score_spread":0.1487174455564377,"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."}}