{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002244879,0.0002761946,0.0006255845,0.0003470578,0.000135982,0.0003776385,0.001310142,0.0001306591,0.000001792041],"category_scores_gemma":[0.001825482,0.0002324678,0.0002756882,0.0002829343,0.00004463141,0.0005708797,0.0001797446,0.0004597361,0.0000497941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005276533,"about_ca_system_score_gemma":0.0005709985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001926905,"about_ca_topic_score_gemma":9.755212e-7,"domain_scores_codex":[0.9966932,0.0001682762,0.001342957,0.0002807443,0.001006214,0.0005086205],"domain_scores_gemma":[0.9959522,0.0005616772,0.001278777,0.0004609636,0.001326096,0.0004203101],"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":[0.00003242014,0.00004692373,0.0002124973,0.00006363154,0.0001021095,0.00001413472,0.001398668,0.9931703,0.00006184218,0.002694126,0.001492521,0.0007108747],"study_design_scores_gemma":[0.0006889433,0.0009555676,0.000009079496,0.000297262,0.00004789133,0.0003383361,0.0006210301,0.9957096,0.0001295666,0.0002528342,0.0007046962,0.0002451722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006082229,0.0008279278,0.9938694,0.0001629525,0.0037145,0.0004671262,3.620311e-7,0.00007838765,0.000271068],"genre_scores_gemma":[0.9159481,0.00001764988,0.08227744,0.00004881873,0.0004985038,0.00001448325,0.000001720615,0.00003738777,0.001155908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9153399,"threshold_uncertainty_score":0.9479762,"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."}}