English
Related papers

Related papers: Ergodic-risk Criterion for Stochastically Stabiliz…

200 papers

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

Whereas classical Markov decision processes maximize the expected reward, we consider minimizing the risk. We propose to evaluate the risk associated to a given policy over a long-enough time horizon with the help of a central limit…

Optimization and Control · Mathematics 2015-12-03 Pengqian Yu , Jia Yuan Yu , Huan Xu

Consider a stochastic process $\{X(t)\}$ on a finite state space $ {\sf X}=\{1,\dots, d\}$. It is conditionally Markov, given a real-valued `input process' $\{\zeta(t)\}$. This is assumed to be small, which is modeled through the scaling,…

Performance · Computer Science 2018-09-18 Yue Chen , Ana Bušić , Sean Meyn

The stochastic processes underlying the growth and stability of biological and psychological systems reveal themselves when far from equilibrium. Far from equilibrium, nonergodicity reigns. Nonergodicity implies that the average outcome for…

Methodology · Statistics 2022-02-03 Madhur Mangalam , Damian G. Kelty-Stephen

We consider the problem of dynamic buying and selling of shares from a collection of $N$ stocks with random price fluctuations. To limit investment risk, we place an upper bound on the total number of shares kept at any time. Assuming that…

Portfolio Management · Quantitative Finance 2009-09-23 Michael J. Neely

We propose a novel randomized linear programming algorithm for approximating the optimal policy of the discounted Markov decision problem. By leveraging the value-policy duality and binary-tree data structures, the algorithm adaptively…

Optimization and Control · Mathematics 2019-06-04 Mengdi Wang

In this paper we study the central limit theorem for additive functionals of stationary Markov chains with general state space by using a new idea involving conditioning with respect to both the past and future of the chain. Practically, we…

Probability · Mathematics 2020-05-19 Magda Peligrad

The class of nonlinear Markov processes is characterized by the dependence of the current state of the process on its current distribution in addition to the dependence on the previous state. Due to this feature, these processes are…

Probability · Mathematics 2022-12-27 Aleksandr Shchegolev

Constructions of numerous approximate sampling algorithms are based on the well-known fact that certain Gibbs measures are stationary distributions of ergodic stochastic differential equations (SDEs) driven by the Brownian motion. However,…

Probability · Mathematics 2020-07-07 Lu-Jing Huang , Mateusz B. Majka , Jian Wang

Stochastic approximation (SA) is a fundamental iterative framework with broad applications in reinforcement learning and optimization. Classical analyses typically rely on martingale difference or Markov noise with bounded second moments,…

Machine Learning · Computer Science 2026-03-23 Siddharth Chandak , Anuj Yadav , Ayfer Ozgur , Nicholas Bambos

Although stochastic optimization is central to modern machine learning, the precise mechanisms underlying its success, and in particular, the precise role of the stochasticity, still remain unclear. Modelling stochastic optimization…

Machine Learning · Statistics 2020-06-12 Liam Hodgkinson , Michael W. Mahoney

We study nonzero-sum stochastic games for continuous time Markov decision processes on a denumerable state space with risk-sensitive ergodic cost criterion. Transition rates and cost rates are allowed to be unbounded. Under a Lyapunov type…

Optimization and Control · Mathematics 2022-07-18 Mrinal K Ghosh , Subrata Golui , Chandan Pal , Somnath Pradhan

This paper studies an optimal control problem for continuous-time stochastic systems subject to reachability objectives specified in a subclass of metric interval temporal logic specifications, a temporal logic with real-time constraints.…

Systems and Control · Computer Science 2015-04-21 Jie Fu , Ufuk Topcu

We investigate the problem of optimal control synthesis for Markov Decision Processes (MDPs), addressing both qualitative and quantitative objectives. Specifically, we require the system to satisfy a qualitative task specified by a Linear…

Systems and Control · Electrical Eng. & Systems 2025-09-19 Yu Chen , Xuanyuan Yin , Shaoyuan Li , Xiang Yin

Entropic risk (ERisk) is an established risk measure in finance, quantifying risk by an exponential re-weighting of rewards. We study ERisk for the first time in the context of turn-based stochastic games with the total reward objective.…

Computer Science and Game Theory · Computer Science 2023-07-14 Christel Baier , Krishnendu Chatterjee , Tobias Meggendorfer , Jakob Piribauer

There is accumulating evidence in the literature that stability of learning algorithms is a key characteristic that permits a learning algorithm to generalize. Despite various insightful results in this direction, there seems to be an…

Machine Learning · Statistics 2019-05-10 Karim Abou-Moustafa , Csaba Szepesvari

Stochastic thermodynamics is the field of study relating fluctuations in stochastic systems to thermodynamic quantities. The total entropy production (EP), is central to the thermodynamic classification of systems. Non-equilibrium systems…

Statistical Mechanics · Physics 2025-08-05 Lars Torbjørn Stutzer

This paper is devoted to solving a time-inconsistent risk-sensitive control problem with parameter $\e$ and its limit case ($\e\rightarrow0^+$) for countable-stated Markov decision processes (MDPs for short). Since the cost functional is…

Optimization and Control · Mathematics 2020-10-22 Hongwei Mei

For a class of linear switched systems in continuous time a controllability condition implies that state feedbacks allow to achieve almost sure stabilization with arbitrary exponential decay rates. This is based on the Multiplicative…

Dynamical Systems · Mathematics 2019-01-11 Fritz Colonius , Guilherme Mazanti

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms…

Machine Learning · Computer Science 2018-09-25 Yue Wang , Wei Chen , Yuting Liu , Zhi-Ming Ma , Tie-Yan Liu
‹ Prev 1 3 4 5 6 7 10 Next ›