{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009614221,0.001112275,0.001026592,0.000347104,0.0003934306,0.0007546504,0.00134892,0.001054132,0.001073579],"category_scores_gemma":[0.002506774,0.0004854361,0.0005943573,0.0002778343,0.000917248,0.0009607854,0.001504004,0.001664469,0.0001976558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009406242,"about_ca_system_score_gemma":0.001135793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008076503,"about_ca_topic_score_gemma":0.005206035,"domain_scores_codex":[0.9996339,0.00008671016,0.00001888701,0.0000995765,0.00008974659,0.00007120131],"domain_scores_gemma":[0.9988833,0.0005969201,0.0001861067,0.00007907997,0.0001773176,0.00007727697],"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":[0.00003369748,0.00003282769,0.0004333071,0.00002556267,0.00002769926,0.00006325077,0.00003512793,0.9797549,0.0009952666,0.001987077,0.0003057825,0.01630558],"study_design_scores_gemma":[0.000003348417,0.00001038318,0.0000251983,0.000001516016,0.00000232464,0.000003709122,0.000001978672,0.9990207,0.0001407213,0.0007315113,0.00005694126,0.00000155625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03770928,0.000334388,0.9585221,0.0002834141,0.00006347297,0.00003667457,0.00002729079,0.000626669,0.002396645],"genre_scores_gemma":[0.9588689,0.0001175297,0.0390362,0.0001368731,0.00002943849,0.00007350717,0.00005065196,0.00003704978,0.001649821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008076503,"threshold_uncertainty_score":0.01605898,"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."}}