横条 发表于 2025-3-28 14:53:01
http://reply.papertrans.cn/88/8790/878995/878995_41.pngjarring 发表于 2025-3-28 22:32:18
Suzanne Graham,Denise Santoss of reinforcement learning have focused on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite sequential decision tasks, formed by temporally concatenating a number of elemental sequential decision tasks. Elemental SIYI’s cannot be decomposed into s