{"id":"W4397019378","doi":"10.1186/s10033-024-01026-4","title":"Reinforcement Learning-Based Energy Management for Hybrid Power Systems: State-of-the-Art Survey, Review, and Perspectives","year":2024,"lang":"en","type":"article","venue":"Chinese Journal of Mechanical Engineering","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; State (computer science); Reinforcement; Energy management; Power (physics); Computer science; Energy (signal processing); Psychology; Artificial intelligence; Social psychology; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005714075,0.0001555842,0.0003189954,0.000113892,0.00002087293,0.00003732481,0.0001219904,0.00002372604,0.000008969948],"category_scores_gemma":[0.0001199962,0.0001026973,0.0001415785,0.0001721143,0.000006621345,0.00009059895,0.00002638694,0.0001651184,4.253699e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006601954,"about_ca_system_score_gemma":0.00001363217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001399935,"about_ca_topic_score_gemma":6.474418e-7,"domain_scores_codex":[0.9991443,0.0000252087,0.000436834,0.00009403841,0.0001619383,0.0001377542],"domain_scores_gemma":[0.9995415,0.0001203441,0.00007053246,0.00009823574,0.000109045,0.00006038171],"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":[0.00001375499,0.000006753555,0.000004360971,0.001601763,0.0001846714,0.000004166578,0.00002234722,0.9962785,0.0005301656,0.0002884376,0.0004396527,0.0006253982],"study_design_scores_gemma":[0.0003355872,0.00008386344,0.00009077661,0.00116193,0.00009459815,0.00002106159,0.000005851256,0.9926886,0.0003422263,0.00002039011,0.005040639,0.0001144537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002545435,0.07498287,0.9213787,0.00009607762,0.0007081597,0.0002067108,0.00000708277,0.00005420701,0.00002080237],"genre_scores_gemma":[0.993964,0.005159147,0.0006813645,0.00001467441,0.00004127545,0.00001404894,0.000003899078,0.00003593068,0.00008566897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9914185,"threshold_uncertainty_score":0.4187873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004552719493750979,"score_gpt":0.1958004720618344,"score_spread":0.1912477525680834,"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."}}