研究人员开发了一种用于函数逼近的熵正则化Q学习中高斯分布逼近的新方法。该研究为异步Q学习生成的平均迭代建立了收敛速率，实现了n^{-1/4}阶的高斯逼近界。这项工作将软贝尔曼递归的线性化与主要鞅项的高斯逼近相结合，还推导了算法最终迭代的高阶矩界。 AI
影响 为Q学习算法建立了理论界限，可能提高强化学习应用中的样本效率。
排序理由 该集群包含一篇详细介绍机器学习新理论结果的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
新的Q学习方法实现了n^{-1/4}的高斯逼近界
报道来源 [2]
-
On Gaussian approximation for entropy-regularized Q-learning with function approximation
arXiv:2605.17678v1 Announce Type: new Abstract: In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy-regularized asynchronous Q-learning with linear function approximation and a poly…
-
On Gaussian approximation for entropy-regularized Q-learning with function approximation
In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy-regularized asynchronous Q-learning with linear function approximation and a polynomial stepsize $k^{-ω}$, $ω\in (1/2,1)$. Assumi…