{"id":"W4389551935","doi":"10.3390/su152416741","title":"Harnessing Online Knowledge Transfer for Enhanced Search and Rescue Decisions via Multi-Agent Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Sustainability","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Benchmark (surveying); Transformative learning; Process (computing); Artificial intelligence; Internet of Things; Machine learning; Computer security","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":[0.001900032,0.0002485411,0.0002988597,0.0002776781,0.0007208951,0.0002255057,0.0006194186,0.000119641,0.00000942725],"category_scores_gemma":[0.00232837,0.0002370387,0.0001314668,0.0009127342,0.0001570376,0.0004281805,0.0006099474,0.0004080176,0.00001873304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005819213,"about_ca_system_score_gemma":0.0004634258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005712956,"about_ca_topic_score_gemma":0.00003972013,"domain_scores_codex":[0.997278,0.0002395654,0.0005369823,0.000737682,0.0003836368,0.0008240833],"domain_scores_gemma":[0.9973239,0.0007227226,0.00003161901,0.0007203136,0.0009867966,0.0002146568],"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":[0.00003189705,0.00007067675,0.0004184643,0.0002385061,0.00002001042,0.000006500335,0.004810723,0.9328805,0.0007493428,0.001911318,0.0000210628,0.05884105],"study_design_scores_gemma":[0.0009989963,0.0002659771,0.008180598,0.0000477795,0.00001163971,0.000001933763,0.0010688,0.9853215,0.001597616,0.0004965307,0.001739361,0.0002693324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1873684,0.00004409457,0.8102975,0.0006984736,0.0001857835,0.001002597,0.000001200322,0.0003645113,0.00003749362],"genre_scores_gemma":[0.9790617,0.00004240898,0.01627634,0.00004321732,0.00005129068,0.000106478,0.00003504809,0.00002646914,0.004357061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7940211,"threshold_uncertainty_score":0.9666159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05112242449648516,"score_gpt":0.3515482704186242,"score_spread":0.3004258459221391,"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."}}