{"id":"W4415428824","doi":"10.3233/faia250817","title":"An Arbitration Control for an Ensemble of Diversified DQN Variants in Continual Reinforcement Learning","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Iterative Learning Control Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Arbitration; Control (management); Context (archaeology); Key (lock); Mechanism (biology)","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":[0.0009691775,0.0005557887,0.0004695622,0.0001790097,0.000235482,0.0007880744,0.001232381,0.0006781539,0.001902683],"category_scores_gemma":[0.00198076,0.0002642227,0.0003709628,0.0002169983,0.0009346878,0.000995784,0.001011014,0.001496153,0.0002673548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007927823,"about_ca_system_score_gemma":0.0005603293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001843315,"about_ca_topic_score_gemma":0.00173849,"domain_scores_codex":[0.9996868,0.00007110331,0.00002184578,0.0001049946,0.00007933901,0.0000358533],"domain_scores_gemma":[0.9995037,0.0002066884,0.00006992368,0.00007816419,0.00008999518,0.00005150133],"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":[0.00009808916,0.0000575372,0.001087262,0.00009084804,0.00006083204,0.0001293003,0.0001423864,0.800405,0.01084247,0.07638923,0.001790315,0.1089068],"study_design_scores_gemma":[0.000007341833,0.00004230651,0.0001102522,0.000008167319,0.000007433026,0.00002356904,0.000004852147,0.984127,0.0008982702,0.01345465,0.001308921,0.000007180616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03677705,0.0008903508,0.9545411,0.000376346,0.0001147141,0.00004222726,0.0000376128,0.0003417813,0.006878691],"genre_scores_gemma":[0.8646442,0.0005039424,0.1277659,0.0001652048,0.00007016827,0.0001030819,0.00005256358,0.00007203568,0.00662289],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001902683,"threshold_uncertainty_score":0.006365061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02543928728161677,"score_gpt":0.2715328186828887,"score_spread":0.2460935314012719,"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."}}