{"id":"W4404864837","doi":"10.1016/j.iot.2024.101447","title":"Adaptive target localization under uncertainty using Multi-Agent Deep Reinforcement Learning with knowledge transfer","year":2024,"lang":"en","type":"article","venue":"Internet of Things","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Transfer of learning; Knowledge transfer; Machine learning; Reinforcement; Knowledge management; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003652484,0.0002394077,0.0002315959,0.0002186717,0.0000748799,0.0002255417,0.000587676,0.00008876849,0.00006787119],"category_scores_gemma":[0.00002805003,0.0001989103,0.00009909063,0.0004022272,0.00009514717,0.0008087065,0.0002111723,0.0003640942,0.00004251633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002928242,"about_ca_system_score_gemma":0.000118612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002571554,"about_ca_topic_score_gemma":0.000008086403,"domain_scores_codex":[0.9983236,0.00009297553,0.0004286219,0.0004225373,0.0004162724,0.0003159471],"domain_scores_gemma":[0.9992779,0.00009667114,0.00009007637,0.0002681735,0.0001857778,0.00008143492],"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":[0.00002219364,0.00002186562,0.0001136863,0.00009976851,0.0001293706,0.00001137922,0.01488577,0.9694164,0.0002487451,0.01423226,0.00003921922,0.000779353],"study_design_scores_gemma":[0.0003292278,0.0003785714,0.00001513846,0.0005844649,0.00003360777,0.00001360665,0.000317081,0.9935063,0.002464924,0.000083717,0.002033628,0.0002397079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002121664,0.0002816813,0.9955448,0.00005773412,0.0003508316,0.0002318406,1.338479e-7,0.0002524864,0.001158818],"genre_scores_gemma":[0.948199,0.00001010182,0.04883598,0.0001353889,0.00002839738,0.000007020275,0.00000790201,0.00003035097,0.002745874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9467088,"threshold_uncertainty_score":0.8111325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03181315952003095,"score_gpt":0.2721559014695192,"score_spread":0.2403427419494883,"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."}}