{"id":"W4417124673","doi":"10.1162/isal.a.858","title":"Genetic Encoding and Shared Knowledge in Reinforcement Learning with Structured Memory","year":2025,"lang":"","type":"article","venue":"ALIFE","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; Encoding (memory); Genetic programming; Reinforcement; Constant (computer programming); Control (management)","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":[0.0008387472,0.0005294186,0.0005198048,0.0003795541,0.0002971548,0.0006163383,0.001177181,0.0007723645,0.001396539],"category_scores_gemma":[0.004315223,0.0002940034,0.0003125223,0.0003176993,0.001125159,0.001202707,0.0008971646,0.0008505726,0.0001176564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000769974,"about_ca_system_score_gemma":0.0008331727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002912472,"about_ca_topic_score_gemma":0.002865256,"domain_scores_codex":[0.9996591,0.0001196369,0.00001921673,0.00008443611,0.00006960943,0.00004806636],"domain_scores_gemma":[0.9985286,0.0008744157,0.0001829722,0.0001928782,0.000142987,0.00007818024],"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":[0.00005351669,0.00004909793,0.000761713,0.00002824772,0.00002206297,0.00008083516,0.000104028,0.9535491,0.00206321,0.01570629,0.0001475846,0.02743434],"study_design_scores_gemma":[0.00002006058,0.00005326825,0.0001252256,0.000007407016,0.000008460142,0.00001737719,0.00001178059,0.9843057,0.0008715937,0.01431098,0.000262107,0.00000608785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1862791,0.0002314494,0.8101274,0.0002454049,0.00003220184,0.00006358071,0.00005124986,0.0005199647,0.002449589],"genre_scores_gemma":[0.9262463,0.00007233948,0.07234613,0.00005159236,0.000007752635,0.0001005521,0.00004443109,0.00003202688,0.001098876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002912472,"threshold_uncertainty_score":0.005791008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01180182249179989,"score_gpt":0.2528365909080778,"score_spread":0.2410347684162779,"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."}}