{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001442542,0.0006918533,0.0006543713,0.0002669242,0.0003878024,0.0007919197,0.001252891,0.0008089314,0.00142172],"category_scores_gemma":[0.005119475,0.0002956221,0.0003414223,0.0002071394,0.001055782,0.001066655,0.0009863973,0.001240137,0.0002563543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006744492,"about_ca_system_score_gemma":0.0007849872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002360653,"about_ca_topic_score_gemma":0.001366228,"domain_scores_codex":[0.999158,0.0003244575,0.00004025157,0.0001856597,0.00018973,0.0001018248],"domain_scores_gemma":[0.9971421,0.00179824,0.0003488755,0.0002437309,0.0002931747,0.0001738521],"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":[0.0001085388,0.0000533443,0.0004558444,0.00004430816,0.00002343889,0.00007792382,0.00006529514,0.9494755,0.001813303,0.02482207,0.0004408561,0.02261951],"study_design_scores_gemma":[0.00001633102,0.00003200696,0.00005040456,0.00000229071,0.00000329218,0.000009396283,0.00000523762,0.9910471,0.0003557166,0.008127902,0.0003471261,0.000003234587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03712673,0.0001363844,0.9588155,0.0001635351,0.00004702676,0.00004055499,0.00002003593,0.0003884977,0.003261698],"genre_scores_gemma":[0.9217573,0.0001220414,0.07525771,0.0001073943,0.00003591241,0.0001161951,0.00003714544,0.00004502682,0.002521195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002360653,"threshold_uncertainty_score":0.007628977,"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."}}