{"id":"W2788842776","doi":"10.3389/frobt.2018.00079","title":"Reactive Reinforcement Learning in Asynchronous Environments","year":2018,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Canada Research Chairs; DeepMind; Canada Foundation for Innovation; Alberta Machine Intelligence Institute","keywords":"Reinforcement learning; Computer science; Asynchronous communication; Markov decision process; Artificial intelligence; Distributed computing; Machine learning; Markov process; Computer network","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003236688,0.0001775283,0.0002295093,0.0002652456,0.0001124952,0.000113365,0.0003975936,0.00009584072,0.000007251619],"category_scores_gemma":[0.00005668733,0.0001864262,0.00002723341,0.0002894235,0.0001428948,0.0004104225,0.0003228846,0.0003931811,0.00002236706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002126594,"about_ca_system_score_gemma":0.0000425918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002487938,"about_ca_topic_score_gemma":0.000004354343,"domain_scores_codex":[0.9985088,0.0000668348,0.0003338771,0.0003893247,0.0002667196,0.0004345196],"domain_scores_gemma":[0.9994326,0.00003097024,0.0001176652,0.0003173965,0.00001710082,0.00008429329],"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":[0.000008892736,0.00002242671,0.06095888,0.000007483456,0.00001291263,0.0000172087,0.001131893,0.9295753,0.00004820316,0.002915082,0.0003804861,0.004921208],"study_design_scores_gemma":[0.0006369367,0.000290202,0.01224697,0.00005701488,0.000004208782,0.000003633626,0.000148051,0.9815795,0.000193144,0.0007143214,0.003889509,0.0002364987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002464577,0.00009572272,0.9935322,0.0004525622,0.0006673289,0.0001837558,8.817147e-8,0.00003539525,0.002568307],"genre_scores_gemma":[0.8924298,0.0001222666,0.1059134,0.0003775616,0.00006371646,0.000008556805,0.000003696001,0.00001503122,0.001065915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8899653,"threshold_uncertainty_score":0.7602239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00789269640831681,"score_gpt":0.2245953956767433,"score_spread":0.2167026992684265,"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."}}