{"id":"W3213721292","doi":"10.4271/14-11-02-0012","title":"A Decentralized Multi-agent Energy Management Strategy Based on a Look-Ahead Reinforcement Learning Approach","year":2021,"lang":"en","type":"article","venue":"SAE International Journal of Electrified Vehicles","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Trois-Rivières","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Process management; Artificial intelligence; Business; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000311666,0.0002536987,0.0002686384,0.0004413074,0.00005858982,0.0001430794,0.0004532474,0.00007445327,0.0001244551],"category_scores_gemma":[0.00003537711,0.0002521885,0.0002195558,0.0002610911,0.00002083653,0.000145322,0.00004732639,0.0003451641,0.0000112736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004681263,"about_ca_system_score_gemma":0.00007269527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001174467,"about_ca_topic_score_gemma":0.00001133231,"domain_scores_codex":[0.9977515,0.00009586446,0.0006565267,0.0002232273,0.0009050028,0.0003678861],"domain_scores_gemma":[0.9991173,0.00006089472,0.0001935197,0.000189153,0.0003065816,0.00013259],"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":[0.0001562679,0.0002172598,0.0001536996,0.00002948453,0.0008064641,0.0004113735,0.00003828634,0.9667926,0.006735437,0.005030476,0.001378038,0.01825056],"study_design_scores_gemma":[0.004664615,0.0002669552,0.002627897,0.0002052163,0.0001084798,0.00007678194,0.0001750026,0.9174782,0.03294644,0.00017511,0.04089074,0.00038454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1174195,0.002258092,0.8409009,0.0007170518,0.00289375,0.0002911021,0.000005481697,0.0003195884,0.03519461],"genre_scores_gemma":[0.992327,0.001149827,0.004995095,0.0003628318,0.0002423767,0.00001823454,0.00004552596,0.00004672002,0.0008123733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8749076,"threshold_uncertainty_score":0.999993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01693551568722451,"score_gpt":0.2386162449683952,"score_spread":0.2216807292811707,"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."}}