English
Related papers

Related papers: High-probability sample complexities for policy ev…

200 papers

In the context of Markov decision processes running in continuous time, one of the most intriguing challenges is the efficient approximation of finite horizon reachability objectives. A multitude of sophisticated model checking algorithms…

Systems and Control · Computer Science 2015-08-03 Yuliya Butkova , Hassan Hatefi , Holger Hermanns , Jan Krcal

Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy. In this paper, we focus on policy evaluation with linear function…

Machine Learning · Computer Science 2017-06-12 Simon S. Du , Jianshu Chen , Lihong Li , Lin Xiao , Dengyong Zhou

We investigate constrained optimal control problems for linear stochastic dynamical systems evolving in discrete time. We consider minimization of an expected value cost over a finite horizon. Hard constraints are introduced first, and then…

Optimization and Control · Mathematics 2011-07-07 Eugenio Cinquemani , Mayank Agarwal , Debasish Chatterjee , John Lygeros

We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove…

Machine Learning · Computer Science 2011-05-02 Shie Mannor , John Tsitsiklis

In this paper, we develop a Topological Approximate Dynamic Programming (TADP) method for planningin stochastic systems modeled as Markov Decision Processesto maximize the probability of satisfying high-level systemspecifications expressed…

Optimization and Control · Mathematics 2020-08-04 Lening Li , Jie Fu

We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given…

Machine Learning · Computer Science 2023-11-07 Jiafan He , Heyang Zhao , Dongruo Zhou , Quanquan Gu

The key assumption underlying linear Markov Decision Processes (MDPs) is that the learner has access to a known feature map $\phi(x, a)$ that maps state-action pairs to $d$-dimensional vectors, and that the rewards and transitions are…

Machine Learning · Computer Science 2023-09-20 Noah Golowich , Ankur Moitra , Dhruv Rohatgi

We consider a dynamic programming (DP) approach to approximately solving an infinite-horizon constrained Markov decision process (CMDP) problem with a fixed initial-state for the expected total discounted-reward criterion with a…

Optimization and Control · Mathematics 2023-08-08 Hyeong Soo Chang

Linear Temporal Logic (LTL) is widely used to specify high-level objectives for system policies, and it is highly desirable for autonomous systems to learn the optimal policy with respect to such specifications. However, learning the…

Machine Learning · Computer Science 2023-10-26 Daqian Shao , Marta Kwiatkowska

We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive…

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

This paper analyzes multi-step temporal difference (TD)-learning algorithms within the ``deadly triad'' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that $n$-step…

Machine Learning · Computer Science 2026-02-24 Han-Dong Lim , Donghwan Lee

This paper studies the approximation of optimal control policies by quantized (discretized) policies for a very general class of Markov decision processes (MDPs). The problem is motivated by applications in networked control systems,…

Optimization and Control · Mathematics 2015-05-14 Naci Saldi , Serdar Yüksel , Tamás Linder

The formal verification and controller synthesis for Markov decision processes that evolve over uncountable state spaces are computationally hard and thus generally rely on the use of approximations. In this work, we consider the…

Systems and Control · Computer Science 2018-11-28 Sofie Haesaert , Sadegh Soudjani , Alessandro Abate

We consider infinite-horizon discounted Markov decision processes and study the convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log-linear policy class. Using the compatible function approximation…

Machine Learning · Computer Science 2023-02-22 Rui Yuan , Simon S. Du , Robert M. Gower , Alessandro Lazaric , Lin Xiao

We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL)…

Systems and Control · Electrical Eng. & Systems 2021-09-29 Krishna C. Kalagarla , Rahul Jain , Pierluigi Nuzzo

We present the first finite-sample analysis of policy evaluation in robust average-reward Markov Decision Processes (MDPs). Prior work in this setting have established only asymptotic convergence guarantees, leaving open the question of…

Machine Learning · Statistics 2025-12-11 Yang Xu , Washim Uddin Mondal , Vaneet Aggarwal

This article deals with stochastic processes endowed with the Markov (memoryless) property and evolving over general (uncountable) state spaces. The models further depend on a non-deterministic quantity in the form of a control input, which…

Systems and Control · Computer Science 2015-09-11 Sofie Haesaert , Robert Babuska , Alessandro Abate

We consider an unconstrained continuous optimization problem where, in each iteration, gradient estimates may be arbitrarily corrupted with a probability greater than 1/2. Additionally, function value estimates may exhibit heavy-tailed…

Optimization and Control · Mathematics 2025-11-25 Katya Scheinberg , Miaolan Xie

The convergence of deterministic policy gradient under the Hadamard parameterization is studied in the tabular setting and the linear convergence of the algorithm is established. To this end, we first show that the error decreases at an…

Optimization and Control · Mathematics 2023-11-28 Jiacai Liu , Jinchi Chen , Ke Wei