{"id":"W4404917641","doi":"10.1016/j.conengprac.2024.106183","title":"A semi-centralized multi-agent RL framework for efficient irrigation scheduling","year":2024,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Multi-agent system; Distributed computing; Scheduling (production processes); Mathematical optimization; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004587845,0.000137494,0.0001229882,0.00008201485,0.0001287244,0.0002464488,0.000267964,0.0000765658,0.000003920345],"category_scores_gemma":[0.0008527822,0.0001382467,0.00009318976,0.0003604272,0.000009903226,0.0004554688,0.00004167044,0.0002367796,0.00005457699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001051611,"about_ca_system_score_gemma":0.00007310694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004847445,"about_ca_topic_score_gemma":9.941688e-8,"domain_scores_codex":[0.9989363,0.00002547279,0.0002216196,0.0003629618,0.0001751506,0.0002784891],"domain_scores_gemma":[0.9979914,0.001418771,0.00005616571,0.0003171621,0.0001180733,0.00009844467],"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":[0.000004253195,0.00005794851,4.899773e-7,0.0000347574,0.00004002421,0.000003806718,0.000155102,0.5863819,0.0005927611,0.4104542,0.0000408525,0.002233987],"study_design_scores_gemma":[0.0004682313,0.00001968091,0.00004964929,0.00008851913,0.00004179801,0.00002062501,0.00001502398,0.9316297,0.00008226033,0.0006623255,0.06677296,0.0001492719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001253619,0.002308032,0.9894817,0.005907438,0.001007014,0.0005129309,0.000009967528,0.000612042,0.00003551287],"genre_scores_gemma":[0.3356122,0.00001815701,0.6636868,0.0001733965,0.0001939577,0.0002527901,0.000004411375,0.00001596305,0.00004237046],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4097918,"threshold_uncertainty_score":0.5637538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596670665170339,"score_gpt":0.2877796791587804,"score_spread":0.271812972507077,"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."}}