{"id":"W4409563182","doi":"10.1007/s13042-025-02622-z","title":"Reward design in multi-agent systems using successor features and multi-information source bayesian optimization","year":2025,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Research Foundation of Korea","keywords":"Successor cardinal; Computational intelligence; Computer science; Bayesian probability; Artificial intelligence; Bayesian optimization; Multi-agent system; Machine learning; Data mining; Mathematics","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":[0.0007216622,0.0001293377,0.000175292,0.0004815334,0.00008529938,0.0005357607,0.0003760734,0.00007629701,0.000001983301],"category_scores_gemma":[0.0004206382,0.0001188549,0.00003320396,0.0001613949,0.00003423195,0.0005762369,0.0001704465,0.000413851,5.621765e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001052299,"about_ca_system_score_gemma":0.00006442394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000130011,"about_ca_topic_score_gemma":0.000003648725,"domain_scores_codex":[0.9986503,0.0002071958,0.0005251314,0.000119424,0.0003615087,0.000136485],"domain_scores_gemma":[0.9989004,0.0001676204,0.0004855854,0.00007559107,0.0003136035,0.00005726194],"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":[0.00002571017,0.00001967767,0.02177362,0.00001898344,0.0000482175,0.00001002051,0.0008407349,0.9709139,0.00003903034,0.0004142009,0.00001622354,0.005879708],"study_design_scores_gemma":[0.001167876,0.00006745873,0.003631685,0.0002474202,0.00001528997,0.0001458675,0.0001406967,0.9936463,0.00003774311,0.00001242659,0.0007848688,0.0001023254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004306024,0.0008323691,0.9937345,0.0004073181,0.0005367105,0.0001007603,5.096571e-7,0.00002193425,0.00005988366],"genre_scores_gemma":[0.722788,0.0004496008,0.2761483,0.00009559526,0.00003350915,0.000001093342,0.000003476211,0.00000691418,0.0004735014],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.718482,"threshold_uncertainty_score":0.5166353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01669915134010129,"score_gpt":0.2864372175682467,"score_spread":0.2697380662281454,"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."}}