Limit-Computable Grains of Truth for Arbitrary Computable Extensive-Form (Un)Known Games
机构 * David R. Cheriton School of Computer Science, University of Waterloo(多伦多大学大卫·R·切里顿计算机科学学院) ; Google DeepMind and Australian National University(谷歌DeepMind和澳大利亚国立大学) ; Anthropic(Anthropic公司) ; Median Group(Median集团)
专题命中 代码与定理证明 :planning(abstract);分类 cs.LG
Comments 42 pages; 2 figures; 7 algorithms