{"id":"W4415196822","doi":"10.1016/j.neunet.2025.108202","title":"Chaos-based reinforcement learning with TD3","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute of Aging; International Research Center for Neurointelligence, University of Tokyo; New Energy and Industrial Technology Development Organization; Japan Science and Technology Agency; Japan Society for the Promotion of Science; University of Tokyo","keywords":"Reinforcement learning; Chaotic; Range (aeronautics); Q-learning; Reinforcement; Learning classifier system; Stability (learning theory); Action (physics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008389381,0.0003644099,0.0006780522,0.0002942106,0.0003761311,0.000613836,0.001006483,0.0008055403,0.004171524],"category_scores_gemma":[0.002406578,0.0002155544,0.0003965071,0.0003015274,0.000591281,0.0005422612,0.001117205,0.0009819859,0.0004200822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005723452,"about_ca_system_score_gemma":0.001046081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004489891,"about_ca_topic_score_gemma":0.003805738,"domain_scores_codex":[0.999761,0.00007306744,0.0000167717,0.00004044934,0.00007430364,0.00003439924],"domain_scores_gemma":[0.9990941,0.0004584977,0.0000617576,0.00008589383,0.0002307476,0.00006894172],"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":[0.0002477267,0.00008801342,0.0007262805,0.00009360567,0.00005801404,0.00007497028,0.00006244831,0.8949406,0.003213067,0.02299071,0.001738125,0.07576653],"study_design_scores_gemma":[0.00001058442,0.00002468384,0.00003384603,0.000002855311,0.000003237868,0.000008708113,0.000001711194,0.9973971,0.0003756948,0.001858328,0.0002798192,0.000003435207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03989783,0.000285591,0.9500949,0.0002895157,0.0001751208,0.0000844972,0.00006184218,0.0006311043,0.008479597],"genre_scores_gemma":[0.9149162,0.00007484909,0.0812744,0.0000977457,0.0000263531,0.0001208897,0.00005234595,0.00006898276,0.003368179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004489891,"threshold_uncertainty_score":0.01395512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007393415344419196,"score_gpt":0.2231342666939981,"score_spread":0.2157408513495788,"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."}}