English
Related papers

Related papers: Hierarchical State Abstractions for Decision-Makin…

200 papers

What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes?In the finite-horizon, undiscounted setting, Dynamic Programming (DP) can only handle these operations efficiently for certain…

Artificial Intelligence · Computer Science 2024-02-20 Alexandre Marthe , Aurélien Garivier , Claire Vernade

We study reinforcement learning in infinite-horizon average-reward settings with linear MDPs. Previous work addresses this problem by approximating the average-reward setting by discounted setting and employing a value iteration-based…

Machine Learning · Computer Science 2025-04-17 Kihyuk Hong , Ambuj Tewari

Under a dramatic increase in mobile data traffic, a promising solution for edge computing systems to maintain their local service is the task migration that may be implemented by means of Autonomous mobile agents (AMA). In designing an…

Systems and Control · Electrical Eng. & Systems 2025-06-12 Khai Doan , Wesley Araujo , Evangelos Kranakis , Ioannis Lambadaris , Yannis Viniotis , Wonjae Shin

A central challenge for intelligent agents in an uncertain world is striking the right balance between utility maximization and resource use, not only for external movement but also for internal computation. Existing theories of control…

Artificial Intelligence · Computer Science 2026-05-19 Itzel Olivos-Castillo , Paul Schrater , Xaq Pitkow

The standard Markov Decision Process (MDP) formulation hinges on the assumption that an action is executed immediately after it was chosen. However, assuming it is often unrealistic and can lead to catastrophic failures in applications such…

Machine Learning · Computer Science 2023-12-14 Esther Derman , Gal Dalal , Shie Mannor

Many decision problems in economics, information technology, and industry can be transformed to an optimal stopping of adapted random vectors with some utility function over the set of Markov times with respect to filtration build by the…

Optimization and Control · Mathematics 2020-11-04 Krzysztof Szajowski

This work presents a multiscale framework to solve a class of stochastic optimal control problems in the context of robot motion planning and control in a complex environment. In order to handle complications resulting from a large decision…

Robotics · Computer Science 2017-03-14 Jung-Su Ha , Han-Lim Choi

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Optimization and Control · Mathematics 2022-06-07 Hyeong Soo Chang

We describe an approach for exploiting structure in Markov Decision Processes with continuous state variables. At each step of the dynamic programming, the state space is dynamically partitioned into regions where the value function is the…

Artificial Intelligence · Computer Science 2012-07-19 Zhengzhu Feng , Richard Dearden , Nicolas Meuleau , Richard Washington

Constrained Markov Decision Processes (CMDPs) are notably more complex to solve than standard MDPs due to the absence of universally optimal policies across all initial state distributions. This necessitates re-solving the CMDP whenever the…

Machine Learning · Computer Science 2025-10-02 Alperen Tercan , Necmiye Ozay

We address the challenge of quantifying Bayesian uncertainty and incorporating it in offline use cases of finite-state Markov Decision Processes (MDPs) with unknown dynamics. Our approach provides a principled method to disentangle…

Machine Learning · Computer Science 2024-06-05 Filippo Valdettaro , A. Aldo Faisal

We propose a diffusion approximation method to the continuous-state Markov Decision Processes (MDPs) that can be utilized to address autonomous navigation and control in unstructured off-road environments. In contrast to most…

Robotics · Computer Science 2024-02-08 Junhong Xu , Kai Yin , Zheng Chen , Jason M. Gregory , Ethan A. Stump , Lantao Liu

We consider a finite-state partially observable Markov decision problem (POMDP) with an infinite horizon and a discounted cost, and we propose a new method for computing a cost function approximation that is based on features and…

Systems and Control · Electrical Eng. & Systems 2025-07-08 Yuchao Li , Kim Hammar , Dimitri Bertsekas

In this paper, we consider risk-sensitive Markov Decision Processes (MDPs) with Borel state and action spaces and unbounded cost under both finite and infinite planning horizons. Our optimality criterion is based on the recursive…

Optimization and Control · Mathematics 2025-10-16 Nicole Bäuerle , Alexander Glauner

High-dimensional motion planning problems can often be solved significantly faster by using multilevel abstractions. While there are various ways to formally capture multilevel abstractions, we formulate them in terms of fiber bundles.…

Robotics · Computer Science 2023-10-24 Andreas Orthey , Sohaib Akbar , Marc Toussaint

Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms. In this paper, we study abstraction in the continuous-control setting. We extend the definition of MDP…

Machine Learning · Computer Science 2022-09-16 Sahand Rezaei-Shoshtari , Rosie Zhao , Prakash Panangaden , David Meger , Doina Precup

We study infinite-horizon Discounted Markov Decision Processes (DMDPs) under a generative model. Motivated by the Algorithm with Advice framework Mitzenmacher and Vassilvitskii 2022, we propose a novel framework to investigate how a…

Machine Learning · Computer Science 2025-02-24 Lixing Lyu , Jiashuo Jiang , Wang Chi Cheung

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 deterministic Markov decision processes (MDPs) and apply max-plus algebra tools to approximate the value iteration algorithm by a smaller-dimensional iteration based on a representation on dictionaries of value functions. The…

Machine Learning · Computer Science 2019-06-21 Francis Bach

Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition probabilities. Unfortunately, accounting for uncertainty in the…

Machine Learning · Computer Science 2020-06-18 Chin Pang Ho , Marek Petrik , Wolfram Wiesemann