{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003275041,0.0001820574,0.0001873505,0.0006540879,0.0001496064,0.0001369461,0.0005342337,0.0000957539,0.000005421499],"category_scores_gemma":[0.00005760039,0.0001785503,0.00003257891,0.001016019,0.0001121409,0.0002953965,0.00002184726,0.0008430419,0.000002156338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037654,"about_ca_system_score_gemma":0.0001081456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001961072,"about_ca_topic_score_gemma":0.000115717,"domain_scores_codex":[0.9984971,0.0001101694,0.0003458443,0.0005331135,0.0002656621,0.0002481629],"domain_scores_gemma":[0.9988717,0.0007073245,0.00006029864,0.0002537908,0.00006000954,0.00004688695],"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":[0.00003384651,0.0001169082,0.002490482,0.00004243895,0.00001731647,0.00002683035,0.001232991,0.5554794,0.00003035794,0.0398877,0.000008993896,0.4006327],"study_design_scores_gemma":[0.0001223819,0.0001427707,0.002213749,0.0004649781,0.000005811116,0.00001217397,0.00007538988,0.9126033,0.001202184,0.0827804,0.0001352117,0.0002416588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02488198,0.00004016723,0.972118,0.00222954,0.0002172259,0.0001601527,0.000003174958,0.0001844629,0.0001653311],"genre_scores_gemma":[0.7016187,0.00002943537,0.2980448,0.0002024813,0.0000108888,0.00003275263,0.000001400848,0.000007108498,0.00005240533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6767367,"threshold_uncertainty_score":0.7281068,"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."}}