{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008978669,0.0004676663,0.0009413025,0.0007530933,0.0002540247,0.0001380643,0.0003449238,0.0004845628,0.00002627354],"category_scores_gemma":[0.00008715515,0.0005881303,0.0001237495,0.0002296774,0.0001946241,0.0003905075,0.00003017367,0.0006810171,0.000006066422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001992969,"about_ca_system_score_gemma":0.0001046997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002116617,"about_ca_topic_score_gemma":0.0003447774,"domain_scores_codex":[0.9968475,0.0001323861,0.001601402,0.0007403095,0.0002281648,0.000450257],"domain_scores_gemma":[0.998453,0.0002499573,0.0004622125,0.0004350071,0.0002762639,0.0001235266],"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":[0.0004456291,0.0001364715,0.0009122822,0.000288214,0.0001508298,0.000001760818,0.002875144,0.4488082,0.006811156,0.4062161,0.0000362839,0.133318],"study_design_scores_gemma":[0.0004756096,0.0005753529,0.0001275316,0.0005113302,0.0001372603,8.033031e-7,0.002948878,0.961659,0.002184377,0.02606081,0.00472485,0.0005941841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008144475,0.000478104,0.9844841,0.00004870026,0.0004397416,0.003805651,0.00007257344,0.00005020374,0.009806483],"genre_scores_gemma":[0.993203,0.0002379001,0.003582479,0.0000397184,0.0002423667,0.0007868739,0.0002235332,0.00004853186,0.001635554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923886,"threshold_uncertainty_score":0.999657,"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."}}