{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004642439,0.001534054,0.003555186,0.001379456,0.0009644001,0.002473632,0.002548298,0.003301131,0.002927007],"category_scores_gemma":[0.0117785,0.002028369,0.001147953,0.001042512,0.002122842,0.003094485,0.002950664,0.002365071,0.0004075067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001952412,"about_ca_system_score_gemma":0.002208036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005932585,"about_ca_topic_score_gemma":0.005326109,"domain_scores_codex":[0.998384,0.0006705606,0.0001057003,0.000282218,0.0003464847,0.0002110626],"domain_scores_gemma":[0.9924819,0.005485164,0.0006274819,0.0001658278,0.0009826618,0.0002568539],"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":[0.00005768188,0.00002813628,0.0001488641,0.00005570373,0.00002800794,0.00003451636,0.00003287612,0.9859719,0.0002523416,0.008820537,0.0001829011,0.004386432],"study_design_scores_gemma":[0.000008997061,0.00001246557,0.0000226877,0.000004221284,0.000004048214,0.000002840162,0.000002016155,0.9970925,0.00005306715,0.002749461,0.0000443679,0.000003359459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01218397,0.000256846,0.9850213,0.0003467132,0.00003748665,0.00006232068,0.00003668055,0.000122649,0.001932085],"genre_scores_gemma":[0.884546,0.0002859872,0.1101927,0.0001591346,0.00007690037,0.00034851,0.0001031474,0.0001240439,0.004163633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005932585,"threshold_uncertainty_score":0.02455187,"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."}}