{"id":"W1980722163","doi":"10.1007/s10846-015-0222-2","title":"Multiple Model Q-Learning for Stochastic Asynchronous Rewards","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Military College of Canada; Carleton University","funders":"","keywords":"Reinforcement learning; Asynchronous communication; Mobile robot; Computer science; Convergence (economics); Stochastic approximation; SIGNAL (programming language); Robot; Relaxation (psychology); Simulation; Real-time computing; Artificial intelligence","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":[0.006669304,0.001359945,0.003713159,0.0009804243,0.0009503745,0.002051198,0.003961516,0.003176947,0.008291143],"category_scores_gemma":[0.02145639,0.001428131,0.001130968,0.001109365,0.002494487,0.003126099,0.003134573,0.003647006,0.0007777187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002711039,"about_ca_system_score_gemma":0.002832623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009780467,"about_ca_topic_score_gemma":0.008133859,"domain_scores_codex":[0.9976926,0.001137233,0.000115847,0.0004357874,0.0003080007,0.0003105301],"domain_scores_gemma":[0.9805138,0.01673536,0.0007704485,0.000508529,0.0009656633,0.0005062846],"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":[0.0001090005,0.00006482615,0.0002805455,0.00008439102,0.00004644152,0.00004872984,0.00004726617,0.9459049,0.000161947,0.0390145,0.0008459356,0.01339149],"study_design_scores_gemma":[0.00001798778,0.0000114235,0.00002561497,0.00000379062,0.000004134504,0.000003460165,0.000002213703,0.9873132,0.00002939094,0.0125119,0.00007311369,0.000003687981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01382507,0.0003648357,0.9830562,0.0005298132,0.00006098161,0.00008011847,0.00007165586,0.0002114939,0.001799919],"genre_scores_gemma":[0.825991,0.0004154355,0.1600613,0.0003679803,0.0001551225,0.000563345,0.0002597256,0.0001852315,0.01200096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009780467,"threshold_uncertainty_score":0.03527105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06013222018714542,"score_gpt":0.2868343053127833,"score_spread":0.2267020851256378,"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."}}