{"id":"W2070060452","doi":"10.1016/j.artint.2007.02.005","title":"A hierarchy of prescriptive goals for multiagent learning","year":2007,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hierarchy; Computer science; Adversary; Multi-agent system; Mathematical optimization; Minification; Artificial intelligence; Mathematics; Machine learning; Economics; Computer security","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":[0.004613495,0.0000882699,0.000176917,0.0001591347,0.0001801674,0.00005188455,0.0005213873,0.00005046372,0.0002856359],"category_scores_gemma":[0.00457586,0.00007188604,0.0001208261,0.0005728393,0.0002322448,0.000125541,0.00007080656,0.0001112152,0.000328298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001504587,"about_ca_system_score_gemma":0.00002803747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002973231,"about_ca_topic_score_gemma":0.00005810898,"domain_scores_codex":[0.9981508,0.00009230417,0.0007636056,0.0003270596,0.0004158596,0.0002503517],"domain_scores_gemma":[0.9956357,0.003262421,0.0002438248,0.0003290017,0.0004415875,0.0000874877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001609732,0.0001158485,0.0003798169,0.000003059658,0.000008929238,8.16938e-7,0.002880775,0.001914702,0.05221812,0.5172825,0.0001369308,0.4248975],"study_design_scores_gemma":[0.00001494697,0.0001081192,0.0004718765,0.000007178317,0.000005988984,7.627327e-7,0.003744134,0.00491879,0.4974951,0.4808938,0.01225859,0.0000806516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2896335,0.00003202236,0.7075385,0.0001790928,0.0001245391,0.0003073011,0.000008513156,0.00002255209,0.002153997],"genre_scores_gemma":[0.9924872,0.00000271334,0.006201555,0.00005715444,0.0000787797,0.0000287796,0.000001768885,0.000007125675,0.001134916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7028537,"threshold_uncertainty_score":0.5478063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3355190226677535,"score_gpt":0.4874850102189569,"score_spread":0.1519659875512034,"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."}}