{"id":"W4416524723","doi":"10.48550/arxiv.2507.00275","title":"Deep Double Q-learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Deep learning; Double loop; Double-precision floating-point format; Carry (investment); Double layered; Double layer (biology); Key (lock)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004204676,0.0003836816,0.000404689,0.0002466143,0.0002502857,0.0003567669,0.002716435,0.000363129,0.00007404465],"category_scores_gemma":[0.0001449144,0.0004051813,0.0002063521,0.0003891783,0.00005614453,0.0002532922,0.005218663,0.001833006,0.0007101145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000155357,"about_ca_system_score_gemma":0.0002803777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007993696,"about_ca_topic_score_gemma":0.000004741238,"domain_scores_codex":[0.9975024,0.0001140291,0.0004836196,0.0009047066,0.0004526606,0.0005425095],"domain_scores_gemma":[0.9976034,0.0001492048,0.0003517837,0.00159781,0.0001748441,0.000122913],"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":[0.00000481295,0.00001401259,0.1024415,0.0001133706,0.00006515353,0.00001764442,0.0005178867,0.8906898,0.00001888215,0.004470807,0.000371285,0.001274824],"study_design_scores_gemma":[0.0006453138,0.000073213,0.0240456,0.0003531529,0.00004835023,0.000004866423,0.00003987555,0.9353493,0.0006721513,0.0004406459,0.03756536,0.0007621988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01818744,0.0002349603,0.9362091,0.0006596885,0.002491207,0.0003197859,3.633385e-7,0.0007821532,0.04111525],"genre_scores_gemma":[0.9069968,0.0002010196,0.03956639,0.0007943736,0.0003829763,0.00008689747,0.00004717689,0.00004123057,0.05188311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8966427,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04371311942963686,"score_gpt":0.2866334611570382,"score_spread":0.2429203417274013,"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."}}