{"id":"W2345097924","doi":"10.1109/tcyb.2015.2509646","title":"A Q-Learning Approach to Flocking With UAVs in a Stochastic Environment","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Flocking (texture); Reinforcement learning; Markov decision process; Computer science; Drone; Q-learning; Mathematical optimization; Markov process; Distributed computing; Artificial intelligence; Mathematics","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":[0.0001935618,0.0002104025,0.0002098823,0.0002150708,0.00009072213,0.00008047083,0.0004921363,0.00007064876,0.00001028349],"category_scores_gemma":[0.000006868663,0.0001547772,0.00005265294,0.0003353186,0.00003533421,0.0001568023,0.000005145791,0.0002083031,0.0002087647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002499162,"about_ca_system_score_gemma":0.00003786656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004350558,"about_ca_topic_score_gemma":0.00002886416,"domain_scores_codex":[0.998268,0.0001019248,0.0002703499,0.0005279966,0.0004193453,0.0004123511],"domain_scores_gemma":[0.999095,0.0001371688,0.00006600774,0.000508389,0.00002509514,0.0001683684],"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":[0.00003795203,0.0003235631,0.00003917724,0.000006355514,0.00003392526,0.00001028202,0.001128264,0.9418593,0.002021508,0.0004863872,0.00001289258,0.05404036],"study_design_scores_gemma":[0.006820632,0.001711145,0.002194484,0.0006821871,0.00007459276,0.0001092978,0.0003372712,0.9770948,0.006230516,0.0001606656,0.00313375,0.001450677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01370424,0.000010153,0.9847373,0.0003202474,0.0001679551,0.0004607647,0.000008110486,0.0001327691,0.0004584115],"genre_scores_gemma":[0.9863148,0.000003998115,0.01274396,0.00005813924,0.00002307758,0.0001798665,4.663502e-7,0.00002265222,0.0006529829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9726106,"threshold_uncertainty_score":0.6311629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01222864924067867,"score_gpt":0.2000832340893112,"score_spread":0.1878545848486325,"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."}}