English
Related papers

Related papers: Is Temporal Difference Learning Optimal? An Instan…

200 papers

In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms,…

Machine Learning · Computer Science 2021-08-09 Semih Cayci , Siddhartha Satpathi , Niao He , R. Srikant

We present a method to find an optimal policy with respect to a reward function for a discounted Markov decision process under general linear temporal logic (LTL) specifications. Previous work has either focused on maximizing a cumulative…

Systems and Control · Electrical Eng. & Systems 2021-03-24 Krishna C. Kalagarla , Rahul Jain , Pierluigi Nuzzo

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning…

Systems and Control · Computer Science 2018-05-18 Arunselvan Ramaswamy , Shalabh Bhatnagar

We propose a unified framework to study policy evaluation (PE) and the associated temporal difference (TD) methods for reinforcement learning in continuous time and space. We show that PE is equivalent to maintaining the martingale…

Machine Learning · Computer Science 2022-02-02 Yanwei Jia , Xun Yu Zhou

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Machine Learning · Computer Science 2021-10-27 Christoph Dann , Teodor V. Marinov , Mehryar Mohri , Julian Zimmert

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

This paper deals with unconstrained discounted continuous-time Markov decision processes in Borel state and action spaces. Under some conditions imposed on the primitives, allowing unbounded transition rates and unbounded (from both above…

Optimization and Control · Mathematics 2011-03-02 Alexey Piunovskiy , Yi Zhang

A default assumption in reinforcement learning (RL) and optimal control is that observations arrive at discrete time points on a fixed clock cycle. Yet, many applications involve continuous-time systems where the time discretization, in…

Machine Learning · Computer Science 2024-01-17 Zichen Zhang , Johannes Kirschner , Junxi Zhang , Francesco Zanini , Alex Ayoub , Masood Dehghan , Dale Schuurmans

Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order…

Systems and Control · Computer Science 2016-06-01 Ezio Bartocci , Luca Bortolussi , Tomǎš Brázdil , Dimitrios Milios , Guido Sanguinetti

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, LTL has the downside that it is sensitive to small…

Logic in Computer Science · Computer Science 2023-05-31 Rajeev Alur , Osbert Bastani , Kishor Jothimurugan , Mateo Perez , Fabio Somenzi , Ashutosh Trivedi

Reinforcement Learning Algorithms are predominantly developed for stationary environments, and the limited literature that considers nonstationary environments often involves specific assumptions about changes that can occur in transition…

Machine Learning · Computer Science 2025-09-25 Ranga Shaarad Ayyagari , Revanth Raj Eega , Ambedkar Dukkipati

We consider approximate dynamic programming for the infinite-horizon stationary $\gamma$-discounted optimal control problem formalized by Markov Decision Processes. While in the exact case it is known that there always exists an optimal…

Optimization and Control · Mathematics 2013-04-23 Boris Lesner , Bruno Scherrer

This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior. We first consider the case in which…

Optimization and Control · Mathematics 2024-05-27 Angeliki Kamoutsi , Peter Schmitt-Förster , Tobias Sutter , Volkan Cevher , John Lygeros

Using insight from numerical approximation of ODEs and the problem formulation and solution methodology of TD learning through a Galerkin relaxation, I propose a new class of TD learning algorithms. After applying the improved numerical…

Machine Learning · Computer Science 2021-04-21 Caleb Bowyer

We provide faster randomized algorithms for computing an $\epsilon$-optimal policy in a discounted Markov decision process with $A_{\text{tot}}$-state-action pairs, bounded rewards, and discount factor $\gamma$. We provide an…

Machine Learning · Computer Science 2024-05-22 Yujia Jin , Ishani Karmarkar , Aaron Sidford , Jiayi Wang

In this paper, we study asymptotic properties of problems of control of stochastic discrete time systems (also known as Markov decision processes) with time averaging and time discounting optimality criteria, and we establish that the…

Optimization and Control · Mathematics 2022-03-09 Konstantin Avrachenkov , Vladimir Gaitsgory , Lucas Gamertsfelder

This paper is devoted to studying constrained continuous-time Markov decision processes (MDPs) in the class of randomized policies depending on state histories. The transition rates may be unbounded, the reward and costs are admitted to be…

Probability · Mathematics 2012-01-04 Xianping Guo , Xinyuan Song

Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we consider Gradient TD algorithms with an additional heavy…

Machine Learning · Computer Science 2021-11-23 Rohan Deb , Shalabh Bhatnagar

Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning. While many TD learning methods have been developed in recent years, little attention has been paid to preserving privacy and most of…

Machine Learning · Computer Science 2022-01-26 Canzhe Zhao , Yanjie Ze , Jing Dong , Baoxiang Wang , Shuai Li