{"id":"W4385945317","doi":"10.1109/tsg.2023.3298807","title":"Graph Multi-Agent Reinforcement Learning for Inverter-Based Active Voltage Control","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Optimal Power Flow Distribution","field":"Engineering","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Partially observable Markov decision process; Computer science; Voltage; Graph; Control theory (sociology); Markov decision process; Voltage regulation; Markov process; Engineering; Control engineering; Markov chain; Control (management); Machine learning; Artificial intelligence; Markov model; Mathematics; Electrical engineering","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":[0.0006216748,0.0006717962,0.000779813,0.0002720117,0.000321749,0.0005057414,0.0008500074,0.0006358042,0.0015098],"category_scores_gemma":[0.001633611,0.000248104,0.000335915,0.0002929455,0.0006105533,0.0004999988,0.0006642998,0.001033651,0.0001597289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008276469,"about_ca_system_score_gemma":0.0009667359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008463968,"about_ca_topic_score_gemma":0.007876725,"domain_scores_codex":[0.9997351,0.00007275584,0.00001071075,0.00006461216,0.00006725755,0.00004966488],"domain_scores_gemma":[0.999335,0.0003546658,0.0001058156,0.00003436767,0.0001275536,0.00004256649],"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":[0.00002536872,0.00002555392,0.0003077966,0.0000232123,0.00001595045,0.00003614088,0.00001972335,0.980962,0.0006202791,0.003731889,0.0003605023,0.01387164],"study_design_scores_gemma":[0.000003174119,0.000008764573,0.00002173685,7.699086e-7,0.000001453154,0.000001953797,0.000001030442,0.999283,0.00005159972,0.000555734,0.00006990917,8.909402e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03075958,0.000301285,0.9647941,0.0002397687,0.00007076552,0.000038242,0.00003416685,0.00036135,0.003400719],"genre_scores_gemma":[0.9720786,0.00009701826,0.02621032,0.00007535562,0.00002265406,0.00005669477,0.00004150637,0.00001906997,0.001398823],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008463968,"threshold_uncertainty_score":0.01682943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01917750196377198,"score_gpt":0.2389090125298473,"score_spread":0.2197315105660753,"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."}}