{"id":"W3110537334","doi":"10.1109/auv50043.2020.9267901","title":"Reinforcement Q-Learning applied to underwater search planning towards maximizing information gain in environments with variable target detection probabilities","year":2020,"lang":"en","type":"article","venue":"","topic":"Underwater Vehicles and Communication Systems","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Sonar; Reinforcement learning; Motion planning; Computer science; Sensitivity (control systems); Underwater; Planner; False alarm; Noise (video); Artificial intelligence; Variable (mathematics); Real-time computing; Path (computing); Machine learning; Engineering; Robot","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":[0.0002190354,0.0001309899,0.0001365704,0.0000991566,0.00007456601,0.0001056732,0.0001328069,0.00005059059,0.00006396216],"category_scores_gemma":[0.000001862632,0.0001149763,0.00001279175,0.0002055748,0.00000970416,0.0003602055,0.00008263212,0.0002044456,0.00007215281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002034694,"about_ca_system_score_gemma":0.00001213314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009010336,"about_ca_topic_score_gemma":0.000005783672,"domain_scores_codex":[0.999077,0.00003149917,0.0003075849,0.0001126643,0.0002226923,0.0002485663],"domain_scores_gemma":[0.9997294,0.0000131469,0.00002409263,0.0001343989,0.00001122394,0.00008774448],"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":[0.00004006174,0.000003408085,0.0003429511,0.00008357047,0.00001572349,2.499137e-7,0.01065158,0.9721102,0.01468157,0.00007332614,0.000006251711,0.001991106],"study_design_scores_gemma":[0.0009319821,0.0002165471,0.0004594594,0.00008487974,0.000005829815,0.000002838736,0.01312997,0.7827477,0.1679763,0.00007947547,0.0339556,0.0004093556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05693379,0.000007461188,0.9282808,0.000111281,0.00001004441,0.0004622047,4.955348e-7,0.000187233,0.01400663],"genre_scores_gemma":[0.9851514,0.000002919072,0.01437381,0.0002027729,0.00001617164,0.0001239834,0.00002305856,0.00001851641,0.00008739388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9282176,"threshold_uncertainty_score":0.4688598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01849899673585734,"score_gpt":0.1961120383201296,"score_spread":0.1776130415842722,"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."}}