English
Related papers

Related papers: The surprising efficiency of temporal difference l…

200 papers

We consider a distributed setup for reinforcement learning, where each agent has a copy of the same Markov Decision Process but transitions are sampled from the corresponding Markov chain independently by each agent. We show that in this…

Machine Learning · Computer Science 2024-06-04 Haoxing Tian , Ioannis Ch. Paschalidis , Alex Olshevsky

The parameters of a discrete stationary Markov model are transition probabilities between states. Traditionally, data consist in sequences of observed states for a given number of individuals over the whole observation period. In such a…

Computation · Statistics 2012-04-30 Alberto Pasanisi , Shuai Fu , Nicolas Bousquet

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD)…

Machine Learning · Computer Science 2020-06-09 Bo Liu , Ian Gemp , Mohammad Ghavamzadeh , Ji Liu , Sridhar Mahadevan , Marek Petrik

Time bounded reachability is a fundamental problem in model checking continuous-time Markov chains (CTMCs) and Markov decision processes (CTMDPs) for specifications in continuous stochastic logics. It can be computed by numerically solving…

Systems and Control · Electrical Eng. & Systems 2020-01-07 Mahmoud Salamati , Sadegh Soudjani , Rupak Majumdar

Designing sample-efficient and computationally feasible reinforcement learning (RL) algorithms is particularly challenging in environments with large or infinite state and action spaces. In this paper, we advance this effort by presenting…

Machine Learning · Computer Science 2024-10-04 Zakaria Mhammedi

Offline policy evaluation is a fundamental statistical problem in reinforcement learning that involves estimating the value function of some decision-making policy given data collected by a potentially different policy. In order to tackle…

Machine Learning · Computer Science 2022-12-20 Juan C. Perdomo , Akshay Krishnamurthy , Peter Bartlett , Sham Kakade

This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain. It is a cornerstone in the analysis of stochastic algorithms in machine learning (e.g. for parameter…

Machine Learning · Statistics 2021-02-02 Alain Durmus , Eric Moulines , Alexey Naumov , Sergey Samsonov , Hoi-To Wai

We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in…

Machine Learning · Statistics 2024-11-19 Taehyun Hwang , Min-hwan Oh

We develop a central limit theorem (CLT) for a non-parametric estimator of the transition matrices in controlled Markov chains (CMCs) with finite state-action spaces. Our results establish precise conditions on the logging policy under…

Statistics Theory · Mathematics 2026-03-26 Ziwei Su , Imon Banerjee , Diego Klabjan

Reinforcement learning (RL) is currently one of the most prominent methods for optimizing dynamical systems, with breakthrough results across various fields. The framework is based on the concept of a Markov decision process (MDP), leading…

Optimization and Control · Mathematics 2025-11-17 Rene Carmona , Mathieu Lauriere

TD($\lambda$) in value-based MARL algorithms or the Temporal Difference critic learning in Actor-Critic-based (AC-based) algorithms synergistically integrate elements from Monte-Carlo simulation and Q function bootstrapping via dynamic…

Machine Learning · Computer Science 2026-05-13 Yue Deng , Zirui Wang , Yin Zhang

Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the…

Machine Learning · Computer Science 2025-10-10 Chongyi Zheng , Ruslan Salakhutdinov , Benjamin Eysenbach

We propose a novel framework of estimating systemic risk measures and risk allocations based on Markov chain Monte Carlo (MCMC) methods. We consider a class of allocations whose jth component can be written as some risk measure of the jth…

Risk Management · Quantitative Finance 2020-05-08 Takaaki Koike , Marius Hofert

Differential temporal difference (TD) methods are value-based reinforcement learning algorithms that have been proposed for infinite-horizon problems. They rely on reward centering, where each reward is centered by the average reward. This…

Machine Learning · Computer Science 2026-05-07 Kris De Asis , Mohamed Elsayed , Jiamin He

Accurate and efficient estimation of rare events probabilities is of significant importance, since often the occurrences of such events have widespread impacts. The focus in this work is on precisely quantifying these probabilities, often…

Methodology · Statistics 2023-05-23 Konstantinos G. Papakonstantinou , Hamed Nikbakht , Elsayed Eshra

We study the evaluation of a policy under best- and worst-case perturbations to a Markov decision process (MDP), using transition observations from the original MDP, whether they are generated under the same or a different policy. This is…

Artificial Intelligence · Computer Science 2024-11-05 Andrew Bennett , Nathan Kallus , Miruna Oprescu , Wen Sun , Kaiwen Wang

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Machine Learning · Computer Science 2020-06-17 Mingde Zhao

Recurrent neural networks for language models like long short-term memory (LSTM) have been utilized as a tool for modeling and predicting long term dynamics of complex stochastic molecular systems. Recently successful examples on learning…

Artificial Intelligence · Computer Science 2021-07-15 Wenqi Zeng , Siqin Cao , Xuhui Huang , Yuan Yao

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal…

Machine Learning · Computer Science 2021-06-09 Emmanuel Bengio , Joelle Pineau , Doina Precup

In a number of applications, particularly in financial and actuarial mathematics, it is of interest to characterize the tail distribution of a random variable $V$ satisfying the distributional equation $V\stackrel{\mathcal{D}}{=}f(V)$,…

Probability · Mathematics 2014-07-04 Jeffrey F. Collamore , Guoqing Diao , Anand N. Vidyashankar