English
Related papers

Related papers: When do discounted-optimal policies also optimize …

200 papers

Separable convex optimization problems with linear ascending inequality and equality constraints are addressed in this paper. Under an ordering condition on the slopes of the functions at the origin, an algorithm that determines the optimum…

Information Theory · Computer Science 2011-07-22 Arun Padakandla , Rajesh Sundaresan

E-variables enable safe and anytime-valid inference, with log-optimal e-variables given by the likelihood ratio of the least favorable distributions (LFDs) when they exist in composite settings. While this unconstrained theory is well…

Methodology · Statistics 2026-04-24 Aytijhya Saha , Aaditya Ramdas

Tandem queueing systems are widely-used stochastic models that arise from many real-life service operations systems. Motivated by the desire to understand the trade-off between the performance and complexity of policies for…

Optimization and Control · Mathematics 2018-04-25 Tonghoon Suk , Xinchang Wang

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 classical problem in ergodic continuous time control consists of studying the limit behavior of the optimal value of a discounted cost functional with infinite horizon as the discount factor $\lambda$ tends to zero. In the literature,…

Optimization and Control · Mathematics 2024-01-23 Piermarco Cannarsa , Stephane Gaubert , Cristian Mendico , Marc Quincampoix

We consider a constrained Markov Decision Problem (CMDP) where the goal of an agent is to maximize the expected discounted sum of rewards over an infinite horizon while ensuring that the expected discounted sum of costs exceeds a certain…

Machine Learning · Computer Science 2024-11-01 Washim Uddin Mondal , Vaneet Aggarwal

We consider an insurance company modelling its surplus process by a Brownian motion with drift. Our target is to maximise the expected exponential utility of discounted dividend payments, given that the dividend rates are bounded by some…

Risk Management · Quantitative Finance 2019-01-23 Julia Eisenberg , Paul Krühner

Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy…

Artificial Intelligence · Computer Science 2017-11-02 Ryo Iwaki , Minoru Asada

We consider the constrained optimal control problem for the gradual-impulsive CTMDP model with the performance criteria being the expected total undiscounted costs (from the running cost and the cost from each time an impulse being…

Optimization and Control · Mathematics 2022-04-07 Alexey Piunovskiy , Yi Zhang

We prove new upper and lower bounds for sample complexity of finding an $\epsilon$-optimal policy of an infinite-horizon average-reward Markov decision process (MDP) given access to a generative model. When the mixing time of the…

Machine Learning · Computer Science 2021-06-15 Yujia Jin , Aaron Sidford

Human preferences are not always represented via complete linear orders: It is natural to employ partially-ordered preferences for expressing incomparable outcomes. In this work, we consider decision-making and probabilistic planning in…

Robotics · Computer Science 2024-10-21 Hazhar Rahmani , Abhishek N. Kulkarni , Jie Fu

Minimizing the peak power consumption and matching demand to supply, under fixed threshold polices, are two key requirements for the success of the future electricity market. In this work, we consider dynamic pricing methods to minimize the…

Optimization and Control · Mathematics 2016-10-26 Zaid Almahmoud , Jacob Crandall , Khaled Elbassioni , Trung Thanh Nguyen , Mardavij Roozbehani

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

Risk-sensitive planning aims to identify policies maximizing some tail-focused metrics in Markov Decision Processes (MDPs). Such an optimization task can be very costly for the most widely used and interpretable metrics such as threshold…

Machine Learning · Statistics 2025-07-09 Alexandre Marthe , Samuel Bounan , Aurélien Garivier , Claire Vernade

Discounting future costs and rewards is a common practice in accounting, game theory, and machine learning. In spite of this, existing logics for reasoning about strategies with cost and resource constraints do not account for discounting.…

Artificial Intelligence · Computer Science 2021-05-12 Lia Bozzone , Pavel Naumov

Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\gamma < 1$, or in episodic settings, with…

Machine Learning · Computer Science 2019-02-11 Silviu Pitis

This note provides a simple example demonstrating that, if exact computations are allowed, the number of iterations required for the value iteration algorithm to find an optimal policy for discounted dynamic programming problems may grow…

Artificial Intelligence · Computer Science 2013-12-25 Eugene A. Feinberg , Jefferson Huang

Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…

Machine Learning · Computer Science 2021-11-24 Thomas Spooner , Nelson Vadori , Sumitra Ganesh

Numerically computing global policies to optimal control problems for complex dynamical systems is mostly intractable. In consequence, a number of approximation methods have been developed. However, none of the current methods can quantify…

Robotics · Computer Science 2021-03-05 Ashwin Khadke , Hartmut Geyer

In this article, we discuss two algorithms tailored to discrete-time deterministic finite-horizon nonlinear optimal control problems or so-called deterministic trajectory optimization problems. Both algorithms can be derived from an…

Optimization and Control · Mathematics 2024-12-10 Mohammad Mahmoudi Filabadi , Tom Lefebvre , Guillaume Crevecoeur