{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022705,0.001020124,0.001067598,0.0005274095,0.0003378103,0.0005909604,0.002282033,0.00100204,0.002291459],"category_scores_gemma":[0.008837788,0.0005453959,0.0004999199,0.0004132474,0.00106253,0.001541315,0.00176874,0.001798146,0.000495108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009669841,"about_ca_system_score_gemma":0.001931556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004701788,"about_ca_topic_score_gemma":0.005700266,"domain_scores_codex":[0.999293,0.0002106936,0.00004399314,0.0001893689,0.0001715987,0.00009139469],"domain_scores_gemma":[0.9976285,0.001434377,0.0001887819,0.0002468864,0.000346981,0.0001545213],"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":[0.000175496,0.0002324328,0.004096305,0.0001812377,0.00007931146,0.00008819199,0.0001438511,0.7434441,0.004194182,0.01154491,0.003568431,0.2322515],"study_design_scores_gemma":[0.00001900562,0.00004456554,0.00008650797,0.00001168574,0.000006809734,0.00001580913,0.000005883495,0.9941922,0.0004722506,0.004625226,0.000516182,0.000003956054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02855257,0.0005230966,0.9670547,0.000279524,0.00008807618,0.00008759928,0.00007112045,0.001174462,0.002168841],"genre_scores_gemma":[0.7019722,0.000398354,0.2925726,0.0007750692,0.00007329643,0.0003148422,0.0002987038,0.0003426351,0.003252314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004701788,"threshold_uncertainty_score":0.01200771,"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."}}