Principled Exploration via Optimistic Bootstrapping and Backward Induction
Chenjia Bai 1 Lingxiao Wang 2 Lei Han 3 Jianye Hao 4 Animesh Garg 5 Peng Liu 1 Zhaoran Wang 2
Abstract 2007; Jin et al., 2018) is a principled approach for efficient
One principled approach for provably efficient exploration with well theoretical guarantees. In tabular
exploration is incorporating the upper confidence cases, the optimism-based methods incorporate th ...


雷达卡




京公网安备 11010802022788号







