Efficiently Solving MDPs with Stochastic Mirror Descent

ICML(2020)

引用 66|浏览208
暂无评分
摘要
We present a unified framework based on primal-dual stochastic mirror descent for approximately solving infinite-horizon Markov decision processes (MDPs) given a generative model. When applied to an average-reward MDP with $A_{tot}$ total state-action pairs and mixing time bound $t_{mix}$ our method computes an $\epsilon$-optimal policy with an expected $\widetilde{O}(t_{mix}^2 A_{tot} \epsilon^{-2})$ samples from the state-transition matrix, removing the ergodicity dependence of prior art. When applied to a $\gamma$-discounted MDP with $A_{tot}$ total state-action pairs our method computes an $\epsilon$-optimal policy with an expected $\widetilde{O}((1-\gamma)^{-4} A_{tot} \epsilon^{-2})$ samples, matching the previous state-of-the-art up to a $(1-\gamma)^{-1}$ factor. Both methods are model-free, update state values and policies simultaneously, and run in time linear in the number of samples taken. We achieve these results through a more general stochastic mirror descent framework for solving bilinear saddle-point problems with simplex and box domains and we demonstrate the flexibility of this framework by providing further applications to constrained MDPs.
更多
查看译文
关键词
mdps
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要