English
Related papers

Related papers: Risk-sensitive safety analysis using Conditional V…

200 papers

We present a general framework for optimizing the Conditional Value-at-Risk for dynamical systems using stochastic search. The framework is capable of handling the uncertainty from the initial condition, stochastic dynamics, and uncertain…

Optimization and Control · Mathematics 2021-02-16 Ziyi Wang , Oswin So , Keuntaek Lee , Camilo A. Duarte , Evangelos A. Theodorou

This paper studies the optimization of Markov decision processes (MDPs) from a risk-seeking perspective, where the risk is measured by conditional value-at-risk (CVaR). The objective is to find a policy that maximizes the long-run CVaR of…

Optimization and Control · Mathematics 2023-12-05 Li Xia , Zhihui Yu , Peter W. Glynn

In this work, we address risk-averse Bayes-adaptive reinforcement learning. We pose the problem of optimising the conditional value at risk (CVaR) of the total return in Bayes-adaptive Markov decision processes (MDPs). We show that a policy…

Machine Learning · Computer Science 2021-10-27 Marc Rigter , Bruno Lacerda , Nick Hawes

Systemic risk measures play a crucial role in analyzing individual losses conditional on extreme system-wide disasters. In this paper, we provide a unified asymptotic treatment for systemic risk measures. First, we classify them into two…

Risk Management · Quantitative Finance 2026-05-26 Bingzhen Geng , Yang Liu , Yimiao Zhao

Autonomous systems are increasingly deployed in real-world environments, where they must achieve high performance while maintaining safety under state and input constraints. Although Model Predictive Control (MPC) provides a principled…

Robotics · Computer Science 2026-04-28 Hao Wang , Nam Nguyen , Armand Jordana , Ludovic Righetti , Somil Bansal

Navigation safety is critical for many autonomous systems such as self-driving vehicles in an urban environment. It requires an explicit consideration of boundary constraints that describe the borders of any infeasible, non-navigable, or…

Robotics · Computer Science 2024-03-25 Junhong Xu , Kai Yin , Jason M. Gregory , Kris Hauser , Lantao Liu

Temporal logics provide a formalism for expressing complex system specifications. A large body of literature has addressed the verification and the control synthesis problem for deterministic systems under such specifications. For…

Logic · Mathematics 2020-08-27 Lars Lindemann , George J. Pappas , Dimos V. Dimarogonas

Safe navigation is a fundamental challenge in multi-robot systems due to the uncertainty surrounding the future trajectory of the robots that act as obstacles for each other. In this work, we propose a principled data-driven approach where…

Robotics · Computer Science 2022-09-19 Atharva Navsalkar , Ashish R. Hota

We consider the portfolio optimization with risk measured by conditional value-at-risk, based on the stress event of chosen asset being equal to the opposite of its value-at-risk level, under the normality assumption. Solvability conditions…

Optimization and Control · Mathematics 2017-03-07 Anna Zalewska

In this paper we present a dynamic programing approach to stochastic optimal control problems with dynamic, time-consistent risk constraints. Constrained stochastic optimal control problems, which naturally arise when one has to consider…

Optimization and Control · Mathematics 2015-11-24 Yin-Lam Chow , Marco Pavone

In financial risk management, Value at Risk (VaR) is widely used to estimate potential portfolio losses. VaR's limitation is its inability to account for the magnitude of losses beyond a certain threshold. Expected Shortfall (ES) addresses…

Risk Management · Quantitative Finance 2024-07-10 Federico Gatta , Fabrizio Lillo , Piero Mazzarisi

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting.…

Machine Learning · Computer Science 2021-03-01 Jianyi Zhang , Paul Weng

Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time. In such cases, it is favorable to adopt a strategy that minimizes the negative…

Systems and Control · Electrical Eng. & Systems 2024-04-05 Siyi Wang , Zifan Wang , Xinlei Yi , Michael M. Zavlanos , Karl H. Johansson , Sandra Hirche

We account for time-varying parameters in the conditional expectile-based value at risk (EVaR) model. The EVaR downside risk is more sensitive to the magnitude of portfolio losses compared to the quantile-based value at risk (QVaR). Rather…

Statistical Finance · Quantitative Finance 2020-09-29 Xiu Xu , Andrija Mihoci , Wolfgang Karl Härdle

We develop a novel framework to assess the risk of misperception in a traffic sign classification task in the presence of exogenous noise. We consider the problem in an autonomous driving setting, where visual input quality gradually…

Robotics · Computer Science 2023-03-17 Guangyi Liu , Disha Kamale , Cristian-Ioan Vasile , Nader Motee

In safety-critical RL settings, the inclusion of an additional cost function is often favoured over the arduous task of modifying the reward function to ensure the agent's safe behaviour. However, designing or evaluating such a cost…

Artificial Intelligence · Computer Science 2025-01-14 Shashank Reddy Chirra , Pradeep Varakantham , Praveen Paruchuri

We study stochastic optimization problems with chance and risk constraints, where in the latter, risk is quantified in terms of the conditional value-at-risk (CVaR). We consider the distributionally robust versions of these problems, where…

Optimization and Control · Mathematics 2020-12-17 Ashish Cherukuri , Ashish R. Hota

Optimizing Conditional Value-at-risk (CVaR) using policy gradient (a.k.a CVaR-PG) faces significant challenges of sample inefficiency. This inefficiency stems from the fact that it focuses on tail-end performance and overlooks many sampled…

Machine Learning · Computer Science 2026-02-06 Yudong Luo , Erick Delage

We introduce the Value-at-Risk Constrained Policy Optimization algorithm (VaR-CPO), a sample efficient and conservative method designed to optimize Value-at-Risk (VaR) constrained reinforcement learning (RL) problems. Empirically, we…

Machine Learning · Computer Science 2026-05-01 Rohan Tangri , Jan-Peter Calliess

Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balance reward…

Machine Learning · Computer Science 2026-04-01 Janaka Chathuranga Brahmanage , Akshat Kumar