arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.07881cs.LG
收藏

基于核嵌入的价值函数逼近的无遗憾强化学习

Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning

Boston University(波士顿大学);The University of Sydney(悉尼大学)

Sayak Ray Chowdhury, Rafael Oliveira

摘要:

我们考虑情景情境下的强化学习(RL)中的后悔最小化问题。在许多现实世界的RL环境中,状态和动作空间是连续的或非常大的。现有的方法建立遗憾的保证,无论是低维表示的随机过渡模型或近似的$Q$ -功能。然而,对状态-价值函数的函数近似方案的理解在很大程度上仍然缺失。在本文中,我们提出了一个在线的基于模型的RL算法,即CME-RL,学习表示的过渡分布作为嵌入在再生核希尔伯特空间,同时仔细平衡开发探索权衡。我们证明了我们的算法的效率,通过证明一个频率论(最坏情况下)的遗憾界是为了$\tilde{O}\big(Hγ_N\sqrt{N}\big)$ \footnote{ $\tilde{O}(\cdot)$ hides only absolute constant and poly-logarithmic factors.},其中$H$是情节长度,$N$是时间步的总数和$γ_N$是一个信息理论量有关的有效尺寸的状态-动作特征空间。我们的方法绕过了估计转移概率的需要,并适用于可以定义内核的任何域。它也带来了新的见解核方法的近似推理和RL遗憾最小化的一般理论。

英文摘要:

We consider the regret minimization problem in reinforcement learning (RL) in the episodic setting. In many real-world RL environments, the state and action spaces are continuous or very large. Existing approaches establish regret guarantees by either a low-dimensional representation of the stochastic transition model or an approximation of the $Q$-functions. However, the understanding of function approximation schemes for state-value functions largely remains missing. In this paper, we propose an online model-based RL algorithm, namely the CME-RL, that learns representations of transition distributions as embeddings in a reproducing kernel Hilbert space while carefully balancing the exploitation-exploration tradeoff. We demonstrate the efficiency of our algorithm by proving a frequentist (worst-case) regret bound that is of order $\tilde{O}\big(Hγ_N\sqrt{N}\big)$\footnote{ $\tilde{O}(\cdot)$ hides only absolute constant and poly-logarithmic factors.}, where $H$ is the episode length, $N$ is the total number of time steps and $γ_N$ is an information theoretic quantity relating the effective dimension of the state-action feature space. Our method bypasses the need for estimating transition probabilities and applies to any domain on which kernels can be defined. It also brings new insights into the general theory of kernel methods for approximate inference and RL regret minimization.

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。

↑