English
Related papers

Related papers: An Optimal Policy for Learning Controllable Dynami…

200 papers

We study a dynamic model of information provision. A state of nature evolves according to a Markov chain. An informed advisor decides how much information to provide to an uninformed decision maker, so as to influence his short-term…

Probability · Mathematics 2014-07-23 Jerome Renault , Eilon Solan , Nicolas Vieille

An informative measurement is the most efficient way to gain information about an unknown state. We present a first-principles derivation of a general-purpose dynamic programming algorithm that returns an optimal sequence of informative…

Machine Learning · Computer Science 2023-02-01 Peter N. Loxley , Ka-Wai Cheung

In this paper, we conduct a literature review of laws of motion based on stochastic search strategies which are mainly focused on exploring highly dynamic environments. In this regard, stochastic search strategies represent an interesting…

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

In this paper, we consider the problem of optimizing the worst-case behavior of a partially observed system. All uncontrolled disturbances are modeled as finite-valued uncertain variables. Using the theory of cost distributions, we present…

Optimization and Control · Mathematics 2023-02-21 Aditya Dave , Nishanth Venkatesh , Andreas A. Malikopoulos

In this paper, we investigate discrete-time decision-making problems in uncertain systems with partially observed states. We consider a non-stochastic model, where uncontrolled disturbances acting on the system take values in bounded sets…

Systems and Control · Electrical Eng. & Systems 2024-07-18 Aditya Dave , Nishanth Venkatesh , Andreas A. Malikopoulos

We consider reinforcement learning in changing Markov Decision Processes where both the state-transition probabilities and the reward functions may vary over time. For this problem setting, we propose an algorithm using a sliding window…

Machine Learning · Computer Science 2018-05-28 Pratik Gajane , Ronald Ortner , Peter Auer

Suppose an online platform wants to compare a treatment and control policy, e.g., two different matching algorithms in a ridesharing system, or two different inventory management algorithms in an online retail site. Standard randomized…

Methodology · Statistics 2022-12-27 Peter Glynn , Ramesh Johari , Mohammad Rasouli

In this paper, we establish a general stochastic maximum principle for optimal control for systems described by a continuous-time Markov regime-switching stochastic recursive utilities model. The control domain is postulated not to be…

Optimization and Control · Mathematics 2019-05-02 Liangquan Zhang , Xun Li

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-next-state…

Optimization and Control · Mathematics 2025-03-18 Mengmeng Li , Daniel Kuhn , Tobias Sutter

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

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control…

Machine Learning · Computer Science 2024-04-03 Ya-Chien Chang , Sicun Gao

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Machine Learning · Computer Science 2024-07-02 Alessio Russo , Alexandre Proutiere

This paper is devoted to studying constrained continuous-time Markov decision processes (MDPs) in the class of randomized policies depending on state histories. The transition rates may be unbounded, the reward and costs are admitted to be…

Probability · Mathematics 2012-01-04 Xianping Guo , Xinyuan Song

A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environments studied in the traditional literature, optimal…

Machine Learning · Computer Science 2024-07-23 Dilip Arumugam , Wanqiao Xu , Benjamin Van Roy

Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several…

Machine Learning · Computer Science 2021-12-17 Mirco Mutti , Mattia Mancassola , Marcello Restelli

A major challenge in reinforcement learning is the design of exploration strategies, especially for environments with sparse reward structures and continuous state and action spaces. Intuitively, if the reinforcement signal is very scarce,…

Machine Learning · Computer Science 2021-06-15 Susan Amin , Maziar Gomrokchi , Hossein Aboutalebi , Harsh Satija , Doina Precup

This paper proposes a novel learning-based framework for autonomous driving based on the concept of maximal safety probability. Efficient learning requires rewards that are informative of desirable/undesirable states, but such rewards are…

Robotics · Computer Science 2024-09-06 Hikaru Hoshino , Jiaxing Li , Arnav Menon , John M. Dolan , Yorie Nakahira

We present a dynamic programming-based solution to a stochastic optimal control problem up to a hitting time for a discrete-time Markov control process. Firstly, we determine an optimal control policy to steer the process toward a compact…

Optimization and Control · Mathematics 2009-09-28 Debasish Chatterjee , Eugenio Cinquemani , Giorgos Chaloulos , John Lygeros

In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the…

Machine Learning · Computer Science 2024-06-04 Guillermo Infante , Anders Jonsson , Vicenç Gómez