{"id":"W4413277282","doi":"10.1109/tetci.2025.3593995","title":"HOBRB: Improving Task Learning With Reward Machines and Bilayer Buffers in a Hierarchical Framework","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Task (project management); Computer science; Bilayer; Artificial intelligence; Psychology; Chemistry; Engineering; Membrane; Systems 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":[0.002315865,0.001079621,0.001401909,0.0005931465,0.0005250401,0.001366777,0.002829859,0.001454238,0.004177629],"category_scores_gemma":[0.006815077,0.00059209,0.0006462553,0.0005202593,0.0009333743,0.002923665,0.00254105,0.00280536,0.001224713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001339031,"about_ca_system_score_gemma":0.002942587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007078315,"about_ca_topic_score_gemma":0.006909228,"domain_scores_codex":[0.9990155,0.0003118636,0.00005336222,0.000231207,0.0002141652,0.0001739664],"domain_scores_gemma":[0.9981561,0.0008804437,0.0001723248,0.0002700702,0.0002839106,0.0002370822],"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":[0.000517186,0.0004459323,0.001568899,0.00017702,0.00007746637,0.00009814357,0.0001986094,0.7260538,0.005683127,0.02408868,0.005257607,0.2358335],"study_design_scores_gemma":[0.00002417093,0.00004971235,0.00005748592,0.000006111835,0.000005694814,0.000005969703,0.000006001686,0.993609,0.0006640073,0.005153936,0.0004127593,0.000005131953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02090469,0.0005006409,0.9733419,0.0003654157,0.00007947123,0.0001039902,0.00008895502,0.002857512,0.001757444],"genre_scores_gemma":[0.6335897,0.0003057539,0.3599561,0.0004409079,0.00008540252,0.0003665329,0.000289498,0.0003295813,0.004636438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007078315,"threshold_uncertainty_score":0.01407427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01479989884701101,"score_gpt":0.3004946006851103,"score_spread":0.2856947018380993,"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."}}