English
Related papers

Related papers: Undiscounted optimal stopping with unbounded rewar…

200 papers

We study optimal multiple stopping of strong Markov processes with random refraction periods. The refraction periods are assumed to be exponentially distributed with a common rate and independent of the underlying dynamics. Our main tool is…

Probability · Mathematics 2016-11-25 Sören Christensen , Jukka Lempa

``When in a difficult situation, it is sometimes better to give up and start all over again''. While this empirical truth has been regularly observed in a wide range of circumstances, quantifying the effectiveness of such a heuristic…

Statistical Mechanics · Physics 2023-02-20 Benjamin De Bruyne , Francesco Mori

This paper addresses objectives tailored to the risk-averse optimization of accumulated rewards in Markov decision processes (MDPs). The studied objectives require maximizing the expected value of the accumulated rewards minus a penalty…

Logic in Computer Science · Computer Science 2024-07-10 Christel Baier , Jakob Piribauer , Maximilian Starke

We investigate the stability of equilibrium-induced optimal values with respect to (w.r.t.) reward functions $f$ and transition kernels $Q$ for time-inconsistent stopping problems under nonexponential discounting in discrete time. First,…

Optimization and Control · Mathematics 2022-05-19 Erhan Bayraktar , Zhenhua Wang , Zhou Zhou

We propose a new approach to solving dynamic decision problems with rewards that are unbounded below. The approach involves transforming the Bellman equation in order to convert an unbounded problem into a bounded one. The major advantage…

Theoretical Economics · Economics 2019-12-02 Qingyin Ma , John Stachurski

We revisit closed-loop performance guarantees for Model Predictive Control in the deterministic and stochastic cases, which extend to novel performance results applicable to receding horizon control of Partially Observable Markov Decision…

Optimization and Control · Mathematics 2020-05-01 Martin A. Sehr , Robert R. Bitmead

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

We study methods based on reproducing kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process (MRP). We study a regularized form of the kernel least-squares temporal difference (LSTD)…

Machine Learning · Statistics 2021-09-27 Yaqi Duan , Mengdi Wang , Martin J. Wainwright

The problem of constrained Markov decision process is considered. An agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its costs (the number of constraints is relatively small). A new dual…

Optimization and Control · Mathematics 2022-10-21 Egor Gladin , Maksim Lavrik-Karmazin , Karina Zainullina , Varvara Rudenko , Alexander Gasnikov , Martin Takáč

We consider optimal stopping problems for a Brownian motion and a geometric Brownian motion with a "disorder", assuming that the moment of a disorder is uniformly distributed on a finite interval. Optimal stopping rules are found as the…

Statistics Theory · Mathematics 2012-12-18 A. N. Shiryaev , M. V. Zhitlukhin

Under non-exponential discounting, we develop a dynamic theory for stopping problems in continuous time. Our framework covers discount functions that induce decreasing impatience. Due to the inherent time inconsistency, we look for…

Optimization and Control · Mathematics 2017-03-13 Yu-Jui Huang , Adrien Nguyen-Huu

Consider the classic infinite-horizon problem of stopping a one-dimensional diffusion to optimise between running and terminal rewards and suppose we are given a parametrised family of such problems. We provide a general theory of parameter…

Probability · Mathematics 2013-02-13 Martin Klimmek

Motivated by robotic surveillance applications, this paper studies the novel problem of maximizing the return time entropy of a Markov chain, subject to a graph topology with travel times and stationary distribution. The return time entropy…

Optimization and Control · Mathematics 2018-05-29 Xiaoming Duan , Mishel George , Francesco Bullo

In distributed model predictive control (DMPC), where a centralized optimization problem is solved in distributed fashion using dual decomposition, it is important to keep the number of iterations in the solution algorithm, i.e. the amount…

Optimization and Control · Mathematics 2013-07-11 Pontus Giselsson , Anders Rantzer

This paper considers an optimal impulse control problem of dynamical systems generated by a flow. The performance criteria are total costs over the infinite time horizon. Apart from the main performance to be minimized, there are multiple…

Optimization and Control · Mathematics 2020-10-27 Alexey Piunovskiy , Yi Zhang

We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfying some long-term constraints during the learning process.…

In this paper we revisit random linear under-determined systems with sparse solutions. We consider $\ell_1$ optimization heuristic known to work very well when used to solve these systems. A collection of fundamental results that relate to…

Optimization and Control · Mathematics 2016-12-20 Mihailo Stojnic

We study reward-free and reward-agnostic exploration in episodic finite-horizon Markov decision processes (MDPs), where an agent explores an unknown environment without observing external rewards. Reward-free exploration aims to enable…

Machine Learning · Computer Science 2026-05-18 Oran Ridel , Alon Cohen

We study a nonstationary bandit problem where rewards depend on both actions and latent states, the latter governed by unknown linear dynamics. Crucially, the state dynamics also depend on the actions, resulting in tension between…

Machine Learning · Computer Science 2025-10-21 Sunmook Choi , Yahya Sattar , Yassir Jedra , Maryam Fazel , Sarah Dean

We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewards (expected scalarized return or ESR) in a multi-objective…

Machine Learning · Computer Science 2025-02-19 Nianli Peng , Muhang Tian , Brandon Fain