{"id":"W7124247083","doi":"10.65109/egea9379","title":"β-DQN: Improving Deep Q-Learning By Evolving the Behavior","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Generality; Simple (philosophy); Function (biology); Range (aeronautics); Population; Overhead (engineering)","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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001513587,0.0005670319,0.0004277111,0.0002417751,0.002149978,0.002895191,0.003438134,0.0002813803,0.0008135707],"category_scores_gemma":[0.0008766137,0.0004492976,0.000271996,0.001558456,0.0002971606,0.001110791,0.002657391,0.001781611,0.0003149953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003249049,"about_ca_system_score_gemma":0.0003231172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002835602,"about_ca_topic_score_gemma":0.00001235365,"domain_scores_codex":[0.9952721,0.0004543608,0.001023581,0.001077138,0.0009058249,0.00126697],"domain_scores_gemma":[0.9965963,0.0007813605,0.0004792027,0.001604245,0.0003615218,0.0001774181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001003302,0.0001264404,0.01716918,0.0001564754,0.0001582267,0.00002551919,0.002193347,0.3750789,0.004119974,0.02117453,0.007926283,0.571861],"study_design_scores_gemma":[0.0004234643,0.0002117559,0.002276196,0.0001205178,0.0001581234,0.00000830289,0.0006318919,0.9762239,0.0009711293,0.00003599506,0.0184518,0.0004869618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008879095,0.002444749,0.9480663,0.00168216,0.002545188,0.001001316,4.434773e-7,0.0003863157,0.04298565],"genre_scores_gemma":[0.8790691,0.0001484891,0.01299938,0.00139946,0.0001263441,0.00013698,0.000004787595,0.00004053857,0.1060749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9350669,"threshold_uncertainty_score":0.9997959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007575819845062511,"score_gpt":0.2448423587692263,"score_spread":0.2372665389241638,"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."}}