English
Related papers

Related papers: On Incorporating Forecasts into Linear State Space…

200 papers

Adaptive time series forecasting is essential for prediction under regime changes. Several classical methods assume linear Gaussian state space model (LGSSM) with variances constant in time. However, there are many real-world processes that…

Machine Learning · Statistics 2024-02-23 Baptiste Abélès , Joseph de Vilmarest , Olivier Wintemberger

Many real-world decision-making problems face the off-dynamics challenge: the agent learns a policy in a source domain and deploys it in a target domain with different state transitions. The distributionally robust Markov decision process…

Machine Learning · Computer Science 2025-05-26 Zhishuai Liu , Pan Xu

We develop methods for estimating how infinitesimal policy changes affect long-term outcomes in dynamic systems. We show that dynamic marginal policy effects (MPEs) can be identified via tractable reduced-form expressions, and can be…

Methodology · Statistics 2026-05-26 I-han Lai , Stefan Wager

We consider Markov decision processes (MDPs) which are a standard model for probabilistic systems. We focus on qualitative properties for MDPs that can express that desired behaviors of the system arise almost-surely (with probability 1) or…

Logic in Computer Science · Computer Science 2014-05-06 Krishnendu Chatterjee , Martin Chmelik , Przemyslaw Daca

Markov decision processes (MDPs) are formal models commonly used in sequential decision-making. MDPs capture the stochasticity that may arise, for instance, from imprecise actuators via probabilities in the transition function. However, in…

Artificial Intelligence · Computer Science 2023-06-21 Marnix Suilen , Thiago D. Simão , David Parker , Nils Jansen

This paper presents expression of mutual information that defines the information gain in planning of sensing resources, when the goal is to reduce the forecast uncertainty of some quantities of interest and the system dynamics is described…

Systems and Control · Computer Science 2013-08-02 Han-Lim Choi

A state space representation of an environment is a classic and yet powerful tool used by many autonomous robotic systems for efficient and often optimal solution planning. However, designing these representations with high performance is…

Machine Learning · Computer Science 2020-12-23 Andrew Wilhelm , Aaron Wilhelm , Garrett Fosdick

State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems. We present a fully Bayesian approach to inference \emph{and learning} (i.e. state estimation and system…

Machine Learning · Statistics 2013-12-18 Roger Frigola , Fredrik Lindsten , Thomas B. Schön , Carl E. Rasmussen

In this paper, we develop a method to automatically generate a control policy for a dynamical system modeled as a Markov Decision Process (MDP). The control specification is given as a Linear Temporal Logic (LTL) formula over a set of…

Robotics · Computer Science 2011-03-24 Xu Chu Ding , Stephen L. Smith , Calin Belta , Daniela Rus

We consider a reinforcement learning (RL) setting in which the agent interacts with a sequence of episodic MDPs. At the start of each episode the agent has access to some side-information or context that determines the dynamics of the MDP…

Machine Learning · Statistics 2019-10-24 Aditya Modi , Nan Jiang , Satinder Singh , Ambuj Tewari

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state. We propose a natural data-driven framework, where the system's dynamics are modelled…

Systems and Control · Computer Science 2019-03-01 Ibrahim Ayed , Emmanuel de Bézenac , Arthur Pajot , Julien Brajard , Patrick Gallinari

We consider risk-sensitive Markov decision processes (MDPs), where the MDP model is influenced by a parameter which takes values in a compact metric space. We identify sufficient conditions under which small perturbations in the model…

Optimization and Control · Mathematics 2022-09-28 Shiping Shao , Abhishek Gupta , William B. Haskell

We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which…

An extension of the idea of state tameness is presented in a dynamic framework. The proposed model for financial markets is rich enough to provide analytical tools that are mostly obtained in models that arise as the solution of SDEs with…

Probability · Mathematics 2008-12-02 Jaime A. Londoño

Accurate and computationally-viable representations of clouds and turbulence are a long-standing challenge for climate model development. Traditional parameterizations that crudely but efficiently approximate these processes are a leading…

Atmospheric and Oceanic Physics · Physics 2024-01-05 Jerry Lin , Mohamed Aziz Bhouri , Tom Beucler , Sungduk Yu , Michael Pritchard

Non-stationary domains, that change in unpredicted ways, are a challenge for agents searching for optimal policies in sequential decision-making problems. This paper presents a combination of Markov Decision Processes (MDP) with Answer Set…

Artificial Intelligence · Computer Science 2017-06-06 Leonardo A. Ferreira , Reinaldo A. C. Bianchi , Paulo E. Santos , Ramon Lopez de Mantaras

We study infinite-horizon robust Markov decision processes (MDPs) on continuous state spaces with structured rectangular ambiguity set. The proposed ambiguity set falls within the convex hull of unknown generating kernels. We utilize the…

Optimization and Control · Mathematics 2026-05-28 Mengmeng Li , Yifan Hu , Daniel Kuhn , Yan Li

Accurately predicting the dynamics of robotic systems is crucial for model-based control and reinforcement learning. The most common way to estimate dynamics is by fitting a one-step ahead prediction model and using it to recursively…

Machine Learning · Computer Science 2021-09-02 Nathan O. Lambert , Albert Wilcox , Howard Zhang , Kristofer S. J. Pister , Roberto Calandra

Decision-making policies for agents are often synthesized with the constraint that a formal specification of behaviour is satisfied. Here we focus on infinite-horizon properties. On the one hand, Linear Temporal Logic (LTL) is a popular…

Artificial Intelligence · Computer Science 2021-06-01 Jan Křetínský

Software-intensive systems, such as software product lines and robotics, utilise Markov decision processes (MDPs) to capture uncertainty and analyse sequential decision-making problems. Despite the usefulness of conventional policy…

Artificial Intelligence · Computer Science 2026-05-01 Alexandros Evangelidis , Gricel Vázquez , Simos Gerasimou
‹ Prev 1 4 5 6 7 8 10 Next ›