经验Bernstein不等式对UCRL2的改进分析
Improved Analysis of UCRL2 with Empirical Bernstein Inequality
摘要:
我们考虑的问题,探索开发的沟通马尔可夫决策过程。我们用经验伯恩斯坦不等式(UCRL 2B)对UCRL 2进行了分析。对于具有$S$状态、$A$动作、$Γ\leq S$下一状态和直径$D$的任何MDP,UCRL 2B的遗憾被限制为$\widetilde{O}(\sqrt{DΓS A T})$。
英文摘要:
We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with $S$ states, $A$ actions, $Γ\leq S$ next states and diameter $D$, the regret of UCRL2B is bounded as $\widetilde{O}(\sqrt{DΓS A T})$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。