{"id":"W4416595599","doi":"10.2139/ssrn.5800802","title":"Toward Zero-Shot Generalization of Deep Reinforcement Learning for Hybrid Energy System Dispatch","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Electric Power System Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Generalization; Generalization error; Normalization (sociology); Generalizability theory; Regularization (linguistics)","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003606739,0.001146581,0.00171019,0.001157172,0.0005118693,0.0002405655,0.00117465,0.0006920143,0.0000263356],"category_scores_gemma":[0.0002368646,0.001307847,0.0009235762,0.0008113398,0.00004466316,0.000348898,0.0003032827,0.003809722,0.000004332816],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01281522,"about_ca_system_score_gemma":0.005052513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004260574,"about_ca_topic_score_gemma":0.000190711,"domain_scores_codex":[0.9896426,0.0005169484,0.003229576,0.0009237888,0.001027706,0.004659428],"domain_scores_gemma":[0.9953656,0.0002088501,0.002248609,0.0007292923,0.0012026,0.0002450813],"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":[0.0001785391,0.00004522377,0.0000956674,0.002616671,0.002054773,0.000003530502,0.0003790018,0.8545704,0.0003753887,0.1288578,0.0000760879,0.01074695],"study_design_scores_gemma":[0.001954501,0.0007289639,0.000004050063,0.001827093,0.0009121891,0.0004403523,0.0006800226,0.9805495,0.004485527,0.006252686,0.001156728,0.001008432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007941878,0.01777994,0.9742641,0.00007786987,0.003343639,0.001269141,0.00001276248,0.0002249515,0.002233395],"genre_scores_gemma":[0.9603369,0.03237911,0.001548858,0.00001642131,0.0007356529,0.0002783069,0.00047963,0.0002042729,0.004020916],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9727153,"threshold_uncertainty_score":0.9989371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009244271775888675,"score_gpt":0.2218974301206986,"score_spread":0.2126531583448099,"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."}}