{"id":"W4407997333","doi":"10.1016/j.est.2025.115428","title":"Deep reinforcement learning for economic battery dispatch: A comprehensive comparison of algorithms and experiment design choices","year":2025,"lang":"en","type":"article","venue":"Journal of Energy Storage","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Faculty of Engineering, McGill University","keywords":"Reinforcement learning; Economic dispatch; Computer science; Battery (electricity); Artificial intelligence; Machine learning; Reinforcement; Mathematical optimization; Engineering; Mathematics; Power (physics); Electric power system; Structural engineering","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":[0.00007936901,0.00009649304,0.0002836801,0.000124064,0.0000396185,0.00002338898,0.00006849596,0.00003918061,0.00001267849],"category_scores_gemma":[0.000005792361,0.00008986748,0.00006310642,0.00002759133,0.00001538376,0.0001003686,0.0000158709,0.00007025836,1.419176e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007879976,"about_ca_system_score_gemma":0.00001811752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000114974,"about_ca_topic_score_gemma":0.000004142336,"domain_scores_codex":[0.9993687,0.00002355848,0.0003904843,0.00006125522,0.00005454643,0.000101466],"domain_scores_gemma":[0.9995567,0.000115388,0.0001856618,0.00005280742,0.00005335795,0.00003605277],"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":[0.00006005122,0.00001228876,0.0001199436,0.00003674435,0.0001461254,9.08849e-7,0.0002027078,0.9873953,0.004421432,0.00008452551,0.000341697,0.007178216],"study_design_scores_gemma":[0.0009036807,0.0001735659,0.0001547564,0.0000565494,0.00004233524,0.000002359508,0.0001793999,0.9777519,0.01244061,0.00001730395,0.008200715,0.0000768899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01635093,0.008641384,0.974461,0.00002603638,0.0003595394,0.00006440219,4.312132e-7,0.00001028598,0.00008599608],"genre_scores_gemma":[0.988347,0.0006778358,0.01076367,0.00003003187,0.00009505035,0.000009202379,0.000003493912,0.00001134235,0.00006237437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9719961,"threshold_uncertainty_score":0.366469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147327854247463,"score_gpt":0.2488367015405714,"score_spread":0.2341039161158252,"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."}}