arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01612cs.LGstat.ML
收藏

基于线性函数逼近和Bandit反馈的MDP在线学习

Online learning in MDPs with linear function approximation and bandit feedback

Universitat Pompeu Fabra(庞培法布拉大学)

Gergely Neu, Julia Olkhovskaya

摘要:

我们考虑一个在线学习问题,其中学习者与马尔可夫决策过程在一系列事件中进行交互,其中允许奖励函数以对抗的方式在事件之间变化,并且学习者只能观察与其行为相关的奖励。我们允许的状态空间是任意大的,但我们假设所有的动作价值函数可以表示为线性函数的一个已知的低维特征映射,学习者可以访问的环境,允许从真正的MDP动态生成轨迹的模拟器。我们的主要贡献是开发一个计算效率高的算法,我们称之为MDP-LinExp 3,并证明其遗憾是有界的$\widetilde{\mathcal{O}}\big(H^2 T^{2/3} (dK)^{1/3}\big)$,其中$T$是情节的数量,$H$是在每个情节的步骤数,$K$是行动的数量,和$d$是特征图的维度。我们还表明,遗憾可以改善$\widetilde{\mathcal{O}}\big(H^2 \sqrt{TdK}\big)$下更强的假设MDP动态。据我们所知,MDP-LinExp 3是第一个可证明有效的算法,这个问题的设置。

英文摘要:

We consider an online learning problem where the learner interacts with a Markov decision process in a sequence of episodes, where the reward function is allowed to change between episodes in an adversarial manner and the learner only gets to observe the rewards associated with its actions. We allow the state space to be arbitrarily large, but we assume that all action-value functions can be represented as linear functions in terms of a known low-dimensional feature map, and that the learner has access to a simulator of the environment that allows generating trajectories from the true MDP dynamics. Our main contribution is developing a computationally efficient algorithm that we call MDP-LinExp3, and prove that its regret is bounded by $\widetilde{\mathcal{O}}\big(H^2 T^{2/3} (dK)^{1/3}\big)$, where $T$ is the number of episodes, $H$ is the number of steps in each episode, $K$ is the number of actions, and $d$ is the dimension of the feature map. We also show that the regret can be improved to $\widetilde{\mathcal{O}}\big(H^2 \sqrt{TdK}\big)$ under much stronger assumptions on the MDP dynamics. To our knowledge, MDP-LinExp3 is the first provably efficient algorithm for this problem setting.

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。

↑