English
Related papers

Related papers: Truncated Variance Reduced Value Iteration

200 papers

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of…

Machine Learning · Statistics 2020-03-17 Koulik Khamaru , Ashwin Pananjady , Feng Ruan , Martin J. Wainwright , Michael I. Jordan

We study infinite-horizon Discounted Markov Decision Processes (DMDPs) under a generative model. Motivated by the Algorithm with Advice framework Mitzenmacher and Vassilvitskii 2022, we propose a novel framework to investigate how a…

Machine Learning · Computer Science 2025-02-24 Lixing Lyu , Jiashuo Jiang , Wang Chi Cheung

We study algorithms using randomized value functions for exploration in reinforcement learning. This type of algorithms enjoys appealing empirical performance. We show that when we use 1) a single random seed in each episode, and 2) a…

Machine Learning · Computer Science 2022-10-14 Zhihan Xiong , Ruoqi Shen , Qiwen Cui , Maryam Fazel , Simon S. Du

The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process. The proposed approach is based on distributed optimization algorithms, which can be interpreted as…

Machine Learning · Computer Science 2025-05-14 Han-Dong Lim , Donghwan Lee

We consider reinforcement learning in changing Markov Decision Processes where both the state-transition probabilities and the reward functions may vary over time. For this problem setting, we propose an algorithm using a sliding window…

Machine Learning · Computer Science 2018-05-28 Pratik Gajane , Ronald Ortner , Peter Auer

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance.…

Optimization and Control · Mathematics 2017-08-24 Li Xia

Policy evaluation via Monte Carlo (MC) simulation is at the core of many MC Reinforcement Learning (RL) algorithms (e.g., policy gradient methods). In this context, the designer of the learning system specifies an interaction budget that…

Machine Learning · Computer Science 2024-10-18 Riccardo Poiani , Nicole Nobili , Alberto Maria Metelli , Marcello Restelli

This paper considers online optimization for a system that performs a sequence of back-to-back tasks. Each task can be processed in one of multiple processing modes that affect the duration of the task, the reward earned, and an additional…

Optimization and Control · Mathematics 2024-01-17 Michael J. Neely

In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common…

Machine Learning · Computer Science 2015-03-19 Prashanth L. A. , Mohammad Ghavamzadeh

The Value Iteration (VI) algorithm is an iterative procedure to compute the value function of a Markov decision process, and is the basis of many reinforcement learning (RL) algorithms as well. As the error convergence rate of VI as a…

Machine Learning · Computer Science 2025-06-12 Jongmin Lee , Amin Rakhsha , Ernest K. Ryu , Amir-massoud Farahmand

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…

Optimization and Control · Mathematics 2020-01-13 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

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…

Machine Learning · Computer Science 2013-10-15 Aviv Tamar , Dotan Di Castro , Shie Mannor

We study the problem of policy evaluation with linear function approximation and present efficient and practical algorithms that come with strong optimality guarantees. We begin by proving lower bounds that establish baselines on both the…

Machine Learning · Statistics 2022-08-16 Tianjiao Li , Guanghui Lan , Ashwin Pananjady

At the working heart of policy iteration algorithms commonly used and studied in the discounted setting of reinforcement learning, the policy evaluation step estimates the value of states with samples from a Markov reward process induced by…

Machine Learning · Computer Science 2021-03-04 Falcon Z. Dai , Matthew R. Walter

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement…

Optimization and Control · Mathematics 2020-04-29 Donghwan Lee , Jianghai Hu

We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs). In this setting, both the reward function and the transition kernel are linear with respect to the given feature maps and are…

Machine Learning · Computer Science 2024-12-24 Han Zhong , Zhongren Chen , Zhuoran Yang , Zhaoran Wang , Csaba Szepesvári

In this paper we present an enhancement of the regression-based variance reduction approaches recently proposed in Belomestny et al. This enhancement is based on a truncation of the control variate and allows for a significant reduction of…

Probability · Mathematics 2017-11-10 Denis Belomestny , Stefan Häfner , Mikhail Urusov

We investigate the optimization of two probabilistic generative models with binary latent variables using a novel variational EM approach. The approach distinguishes itself from previous variational approaches by using latent states as…

Machine Learning · Statistics 2018-02-26 Jörg Lücke , Zhenwen Dai , Georgios Exarchakis

Many large-scale stochastic optimization algorithms involve repeated solutions of linear systems or evaluations of log-determinants. In these regimes, computing exact solutions is often unnecessary; it is more computationally efficient to…

Numerical Analysis · Mathematics 2026-02-24 Tianshi Xu , Difeng Cai , Hua Huang , Edmond Chow , Yuanzhe Xi

Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood. Performing Bayesian parameter inference in this context can be challenging. We present a neural…

Machine Learning · Statistics 2021-10-27 Benjamin Kurt Miller , Alex Cole , Patrick Forré , Gilles Louppe , Christoph Weniger