This paper presents new \emph{variance-aware} confidence sets for linear bandits and linear mixture Markov Decision Processes (MDPs). With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an $\tilde{O}(poly(d)\sqrt{1 + \sum_{k=1}^{K}\sigma_k^2})$ data-dependent regret bound, where $d$ is the feature dimension, $K$ is the number of rounds, and $\sigma_k^2$ is the \emph{unknown} variance of the reward at the $k$-th round. This is the first regret bound that only scales with the variance and the dimension but \emph{no explicit polynomial dependency on $K$}. When variances are small, this bound can be significantly smaller than the $\tilde{\Theta}\left(d\sqrt{K}\right)$ worst-case regret bound. For linear mixture MDPs, we obtain an $\tilde{O}(poly(d, \log H)\sqrt{K})$ regret bound, where $d$ is the number of base models, $K$ is the number of episodes, and $H$ is the planning horizon. This is the first regret bound that only scales \emph{logarithmically} with $H$ in the reinforcement learning with linear function approximation setting, thus \emph{exponentially improving} existing results, and resolving an open problem in \citep{zhou2020nearly}. We develop three technical ideas that may be of independent interest: 1) applications of the peeling technique to both the input norm and the variance magnitude, 2) a recursion-based estimator for the variance, and 3) a new convex potential lemma that generalizes the seminal elliptical potential lemma.


翻译:本文为线性土匪和线性混合 Markov 决策过程提供了新的 emph{ variance- aware} 信任 。 在新的信任 中, 我们得到了以下的框框 : 对于线性土匪, 我们得到了$\ tilde{ O} (poly(d)\ qrt{ 1 +\ sum ⁇ k= 1\ k\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\

0
下载
关闭预览

相关内容

专知会员服务
16+阅读 · 2020年12月4日
因果图,Causal Graphs,52页ppt
专知会员服务
238+阅读 · 2020年4月19日
深度强化学习策略梯度教程,53页ppt
专知会员服务
176+阅读 · 2020年2月1日
强化学习最新教程,17页pdf
专知会员服务
167+阅读 · 2019年10月11日
已删除
将门创投
3+阅读 · 2019年4月12日
Hierarchical Imitation - Reinforcement Learning
CreateAMind
19+阅读 · 2018年5月25日
Arxiv
0+阅读 · 2021年12月30日
Arxiv
11+阅读 · 2020年12月2日
Arxiv
3+阅读 · 2018年2月24日
VIP会员
相关资讯
已删除
将门创投
3+阅读 · 2019年4月12日
Hierarchical Imitation - Reinforcement Learning
CreateAMind
19+阅读 · 2018年5月25日
Top
微信扫码咨询专知VIP会员