{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002635016,0.0002423511,0.0002242003,0.0002361369,0.0002436727,0.0001278523,0.001140954,0.0001112852,0.0001325156],"category_scores_gemma":[0.00009017303,0.0002545663,0.0001924658,0.0005088369,0.00006478126,0.0002145139,0.0002688528,0.0003326099,0.0003050719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509245,"about_ca_system_score_gemma":0.000103119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001808382,"about_ca_topic_score_gemma":0.000003536901,"domain_scores_codex":[0.9983798,0.00008870426,0.0001977185,0.0006490138,0.0001534631,0.000531305],"domain_scores_gemma":[0.9984557,0.0003095905,0.0002085072,0.000754444,0.0001186448,0.0001530891],"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":[0.00004666865,0.00001433147,0.005653663,0.00003703729,0.00003463506,0.00001152257,0.00017352,0.9529998,0.0001816802,0.04028652,0.00003438069,0.0005262506],"study_design_scores_gemma":[0.001175895,0.0003663198,0.0007773066,0.000026015,0.00001932556,0.000001364645,0.00006662872,0.9893168,0.000471245,0.0003534583,0.007094689,0.0003309969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1080473,0.00001042135,0.8864327,0.00006926331,0.0002583375,0.0004143211,2.394353e-7,0.0002748595,0.004492511],"genre_scores_gemma":[0.987429,0.00000508367,0.004032891,0.0002635875,0.00004190121,0.000001650998,0.000008679677,0.00002290239,0.008194314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8823998,"threshold_uncertainty_score":0.9999906,"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."}}