中文
相关论文

相关论文: Statistical guarantees for continuous-time policy …

200 篇论文

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$.…

机器学习 · 统计学 2025-01-17 Yang Peng , Liangyu Zhang , Zhihua Zhang

We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) as an improved…

机器学习 · 计算机科学 2017-12-29 Huizhen Yu

We propose a stochastic approximation (SA) based method with randomization of samples for policy evaluation using the least squares temporal difference (LSTD) algorithm. Our proposed scheme is equivalent to running regular temporal…

机器学习 · 计算机科学 2020-01-27 L. A. Prashanth , Nathaniel Korda , Rémi Munos

In this paper we extend temporal difference policy evaluation algorithms to performance criteria that include the variance of the cumulative reward. Such criteria are useful for risk management, and are important in domains such as finance…

机器学习 · 计算机科学 2013-10-15 Aviv Tamar , Dotan Di Castro , Shie Mannor

Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this paper, we study the sampling efficiency of score-based discrete diffusion models under a…

机器学习 · 计算机科学 2026-02-17 Daniil Dmitriev , Zhihan Huang , Yuting Wei

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple…

机器学习 · 统计学 2024-06-18 Sergey Samsonov , Daniil Tiapkin , Alexey Naumov , Eric Moulines

We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control policy, working together to discover the…

最优化与控制 · 数学 2020-01-13 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

We establish novel and general high-dimensional concentration inequalities and Berry-Esseen bounds for vector-valued martingales induced by Markov chains. We apply these results to analyze the performance of the Temporal Difference (TD)…

机器学习 · 统计学 2026-05-22 Weichen Wu , Yuting Wei , Alessandro Rinaldo

Given a dataset on actions and resulting long-term rewards, a direct estimation approach fits value functions that minimize prediction error on the training data. Temporal difference learning (TD) methods instead fit value functions by…

机器学习 · 计算机科学 2024-02-15 David Cheikhi , Daniel Russo

Continuous diffusion models have demonstrated remarkable performance in data generation across various domains, yet their efficiency remains constrained by two critical limitations: (1) the local adjacency structure of the forward Markov…

机器学习 · 统计学 2025-05-29 Xunpeng Huang , Yingyu Lin , Nikki Lijing Kuang , Hanze Dong , Difan Zou , Yian Ma , Tong Zhang

In this paper we present a novel method for estimating the parameters of a parametric diffusion processes. Our approach is based on a closed-form Maximum Likelihood estimator for an approximating Continuous Time Markov Chain (CTMC) of the…

统计方法学 · 统计学 2021-08-31 J. L. Kirkby , Dang Nguyen , Duy Nguyen , Nhu Nguyen

We study stochastic approximation procedures for approximately solving a $d$-dimensional linear fixed point equation based on observing a trajectory of length $n$ from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the…

最优化与控制 · 数学 2024-05-14 Wenlong Mou , Ashwin Pananjady , Martin J. Wainwright , Peter L. Bartlett

This paper deals with ergodic theorems for particular time-inhomogeneous Markov processes, whose the time-inhomogeneity is asymptotically periodic. Under a Lyapunov/minorization condition, it is shown that, for any measurable bounded…

概率论 · 数学 2022-04-06 William Oçafrain

We propose an analytic approach for the steady-state dynamics of Markov processes on locally tree-like graphs. It is based on time-translation invariant probability distributions for edge trajectories, which we encode in terms of infinite…

统计力学 · 物理学 2025-09-08 Stefano Crotti , Thomas Barthel , Alfredo Braunstein

This work provides test error bounds for iterative fixed point methods on linear predictors -- specifically, stochastic and batch mirror descent (MD), and stochastic temporal difference learning (TD) -- with two core contributions: (a) a…

机器学习 · 计算机科学 2022-06-29 Matus Telgarsky

Diffusion models have achieved great success in generating high-dimensional samples across various applications. While the theoretical guarantees for continuous-state diffusion models have been extensively studied, the convergence analysis…

机器学习 · 计算机科学 2025-04-15 Zikun Zhang , Zixiang Chen , Quanquan Gu

We study non-parametric estimation of the value function of an infinite-horizon $\gamma$-discounted Markov reward process (MRP) using observations from a single trajectory. We provide non-asymptotic guarantees for a general family of…

机器学习 · 统计学 2022-11-09 Yaqi Duan , Martin J. Wainwright

We quantify the efficiency of temporal difference (TD) learning over the direct, or Monte Carlo (MC), estimator for policy evaluation in reinforcement learning, with an emphasis on estimation of quantities related to rare events. Policy…

机器学习 · 计算机科学 2025-01-17 Xiaoou Cheng , Jonathan Weare

We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. Compared with intensive research efforts in finite sample…

机器学习 · 计算机科学 2024-10-01 Tianjiao Li , Feiyang Wu , Guanghui Lan

This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the…

机器学习 · 统计学 2015-04-06 Kamil Ciosek
‹ 上一页 1 2 3 10 下一页 ›