{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002371128,0.0007687858,0.001137655,0.0004618187,0.0004015563,0.0005974148,0.0009603662,0.0007957344,0.0009852833],"category_scores_gemma":[0.007811338,0.0003520481,0.0002817156,0.0005187362,0.001304284,0.0005556703,0.0008548545,0.0008438267,0.0001195785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001110014,"about_ca_system_score_gemma":0.001809263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01249361,"about_ca_topic_score_gemma":0.004600255,"domain_scores_codex":[0.9993483,0.0003591594,0.00002402355,0.00006905627,0.000121591,0.00007779043],"domain_scores_gemma":[0.9941528,0.004724939,0.0003000904,0.0001245168,0.0005486597,0.0001489576],"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":[0.00002822041,0.00002277999,0.000237249,0.00001869963,0.00000765443,0.00002178688,0.00002486944,0.9904546,0.0003518374,0.001288971,0.00006820375,0.007475188],"study_design_scores_gemma":[0.000007827271,0.00002917735,0.00004065286,0.000002022918,0.000001643575,0.000003562969,0.000002735032,0.9991116,0.0001204995,0.0006348779,0.00004372652,0.000001644788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08558847,0.0002724594,0.9103787,0.0002660314,0.00003346758,0.0001365711,0.00001860692,0.0003167149,0.002989024],"genre_scores_gemma":[0.9450126,0.00009188551,0.05410846,0.0000516486,0.00001433096,0.0000868349,0.00001380848,0.00001753385,0.0006029247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01249361,"threshold_uncertainty_score":0.02484179,"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."}}