English
Related papers

Related papers: Runtime Monitoring for Markov Decision Processes

200 papers

We develop a method for computing policies in Markov decision processes with risk-sensitive measures subject to temporal logic constraints. Specifically, we use a particular risk-sensitive measure from cumulative prospect theory, which has…

Artificial Intelligence · Computer Science 2020-04-21 Murat Cubuktepe , Ufuk Topcu

We present exact algorithms for identifying deterministic-actions effects and preconditions in dynamic partially observable domains. They apply when one does not know the action model(the way actions affect the world) of a domain and must…

Artificial Intelligence · Computer Science 2014-01-16 Eyal Amir , Allen Chang

Reactive (memoryless) policies are sufficient in completely observable Markov decision processes (MDPs), but some kind of memory is usually necessary for optimal control of a partially observable MDP. Policies with finite memory can be…

Artificial Intelligence · Computer Science 2013-01-30 Nicolas Meuleau , Leonid Peshkin , Kee-Eung Kim , Leslie Pack Kaelbling

Modeling unknown systems from data is a precursor of system optimization and sequential decision making. In this paper, we focus on learning a Markov model from a single trajectory of states. Suppose that the transition model has a small…

Methodology · Statistics 2020-11-30 Ziwei Zhu , Xudong Li , Mengdi Wang , Anru Zhang

In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors, inducing confounding and biasing estimates…

Machine Learning · Computer Science 2023-03-24 Andrew Bennett , Nathan Kallus

The problem of detection and possible estimation of a signal generated by a dynamic system when a variable number of noisy measurements can be taken is here considered. Assuming a Markov evolution of the system (in particular, the pair…

Information Theory · Computer Science 2022-05-12 Emanuele Grossi , Marco Lops

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (or minimize…

Optimization and Control · Mathematics 2015-07-07 Mahmoud El Chamie , Behcet Acikmese

Partial Observability -- where agents can only observe partial information about the true underlying state of the system -- is ubiquitous in real-world applications of Reinforcement Learning (RL). Theoretically, learning a near-optimal…

Machine Learning · Computer Science 2022-12-19 Fan Chen , Yu Bai , Song Mei

Complex and nonlinear dynamical systems often involve parameters that change with time, accurate tracking of which is essential to tasks such as state estimation, prediction, and control. Existing machine-learning methods require full state…

Machine Learning · Computer Science 2023-11-16 Zheng-Meng Zhai , Mohammadamin Moradi , Bryan Glaz , Mulugeta Haile , Ying-Cheng Lai

Robots are increasingly used to carry out critical missions in extreme environments that are hazardous for humans. This requires a high degree of operational autonomy under uncertain conditions, and poses new challenges for assuring the…

Artificial Intelligence · Computer Science 2020-12-08 Xingyu Zhao , Valentin Robu , David Flynn , Fateme Dinmohammadi , Michael Fisher , Matt Webster

In this paper, we introduce a probabilistic approach to risk assessment of robot systems by focusing on the impact of uncertainties. While various approaches to identifying systematic hazards (e.g., bugs, design flaws, etc.) can be found in…

Robotics · Computer Science 2024-10-28 Woo-Jeong Baek , Tom P. Huck , Joschka Haas , Jonas Lewandrowski , Tamim Asfour , Torsten Kröger

Decision-theoretic planning with risk-sensitive planning objectives is important for building autonomous agents or decision-support systems for real-world applications. However, this line of research has been largely ignored in the…

Artificial Intelligence · Computer Science 2012-07-09 Yaxin Liu , Sven Koenig

We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive…

Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assurances on the system's risk established beforehand. Common…

Machine Learning · Statistics 2025-06-23 Alexander Timans , Rajeev Verma , Eric Nalisnick , Christian A. Naesseth

We investigate partially observed Markov decision processes (POMDPs) with cost functions regularized by entropy terms describing state, observation, and control uncertainty. Standard POMDP techniques are shown to offer bounded-error…

Systems and Control · Electrical Eng. & Systems 2023-05-10 Timothy L. Molloy , Girish N. Nair

This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control…

Systems and Control · Electrical Eng. & Systems 2021-03-23 Hossein Nejatbakhsh Esfahani , Arash Bahari Kordabad , Sebastien Gros

In piecewise-deterministic Markov processes (PDMPs) the state of a finite-dimensional system evolves continuously, but the evolutive equation may change randomly as a result of discrete switches. A running cost is integrated along the…

Optimization and Control · Mathematics 2023-02-27 Elliot Cartee , Antonio Farah , April Nellis , Jacob van Hook , Alexander Vladimirsky

A robust model predictive control scheme for a class of constrained norm-bounded uncertain discrete-time linear systems is developed under the hypothesis that only partial state measurements are available for feedback. Off-line calculations…

Systems and Control · Computer Science 2018-07-23 Giuseppe Franzè , Massimiliano Mattei , Luciano Ollio , Valerio Scordamaglia

Probabilistic modeling provides the capability to represent and manipulate uncertainty in data, models, predictions and decisions. We are concerned with the problem of learning probabilistic models of dynamical systems from measured data.…

Computation · Statistics 2018-03-14 Thomas B. Schön , Andreas Svensson , Lawrence Murray , Fredrik Lindsten

When designing optimal controllers for any system, it is often the case that the true state of the system is unknown to the controller, for example due to noisy measurements or partially observable states. Incomplete state information must…

Optimization and Control · Mathematics 2014-01-23 Kendra Lesser , Meeko Oishi
‹ Prev 1 4 5 6 7 8 10 Next ›