اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدRisk-sensitive safety analysis using Conditional Value-at-Risk
184
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
This paper develops a safety analysis method for stochastic systems that is sensitive to the possibility and severity of rare harmful outcomes. We define risk-sensitive safe sets as sub-level sets of the solution to a non-standard optimal control problem, where a random maximum cost is assessed using the Conditional Value-at-Risk (CVaR) functional. The solution to the control problem represents the maximum extent of constraint violation of the state trajectory, averaged over the $alphacdot 100$% worst cases, where $alpha in (0,1]$. This problem is well-motivated but difficult to solve in a tractable fashion because temporal decompositions for risk functionals generally depend on the history of the systems behavior. Our primary theoretical contribution is to derive under-approximations to risk-sensitive safe sets, which are computationally tractable. Our method provides a novel, theoretically guaranteed, parameter-dependent upper bound to the CVaR of a maximum cost without the need to augment the state space. For a fixed parameter value, the solution to only one Markov decision process problem is required to obtain the under-approximations for any family of risk-sensitivity levels. In addition, we propose a second definition for risk-sensitive safe sets and provide a tractable method for their estimation without using a parameter-dependent upper bound. The second definition is expressed in terms of a new coherent risk functional, which is inspired by CVaR. We demonstrate our primary theoretical contribution using numerical examples of a thermostatically controlled load system and a stormwater system.
قيم البحث
اقرأ أيضاً
This paper proposes a safety analysis method that facilitates a tunable balance between the worst-case and risk-neutral perspectives. First, we define a risk-sensitive safe set to specify the degree of safety attained by a stochastic system. This set
is defined as a sublevel set of the solution to an optimal control problem that is expressed using the Conditional Value-at-Risk (CVaR) measure. This problem does not satisfy Bellmans Principle, thus our next contribution is to show how risk-sensitive safe sets can be under-approximated by the solution to a CVaR-Markov Decision Process. We adopt an existing value iteration algorithm to find an approximate solution to the reduced problem for a class of linear systems. Then, we develop a realistic numerical example of a stormwater system to show that this approach can be applied to non-linear systems. Finally, we compare the CVaR criterion to the exponential disutility criterion. The latter allocates control effort evenly across the cost distribution to reduce variance, while the CVaR criterion focuses control effort on a given worst-case quantile--where it matters most for safety.
Risk-sensitive safety analysis is a safety analysis method for stochastic systems on Borel spaces that uses a risk functional from finance called Conditional Value-at-Risk (CVaR). CVaR provides a particularly expressive way to quantify the safety of
a control system, as it represents the average cost in a fraction of worst cases. In prior work, the notion of a risk-sensitive safe set was defined in terms of a non-standard optimal control problem, in which a maximum cost is assessed via CVaR. Here, we provide a method to compute risk-sensitive safe sets exactly in principle by utilizing a state-space augmentation technique. In addition, we prove the existence of an optimal pre-commitment policy under a measurable selection condition. The proposed framework assumes continuous system dynamics and cost functions, but is otherwise flexible. In particular, it can accommodate probabilistic control policies, fairly general disturbance distributions, and control-dependent, non-monotonic, and non-convex stage costs. We demonstrate how risk-sensitive safety analysis is useful for a stormwater infrastructure application. Our numerical examples are inspired by current challenges that cities face in managing precipitation uncertainty.
The standard approach to risk-averse control is to use the Exponential Utility (EU) functional, which has been studied for several decades. Like other risk-averse utility functionals, EU encodes risk aversion through an increasing convex mapping $var
phi$ of objective costs to subjective costs. An objective cost is a realization $y$ of a random variable $Y$. In contrast, a subjective cost is a realization $varphi(y)$ of a random variable $varphi(Y)$ that has been transformed to measure preferences about the outcomes. For EU, the transformation is $varphi(y) = exp(frac{-theta}{2}y)$, and under certain conditions, the quantity $varphi^{-1}(E(varphi(Y)))$ can be approximated by a linear combination of the mean and variance of $Y$. More recently, there has been growing interest in risk-averse control using the Conditional Value-at-Risk (CVaR) functional. In contrast to the EU functional, the CVaR of a random variable $Y$ concerns a fraction of its possible realizations. If $Y$ is a continuous random variable with finite $E(|Y|)$, then the CVaR of $Y$ at level $alpha$ is the expectation of $Y$ in the $alpha cdot 100 %$ worst cases. Here, we study the applications of risk-averse functionals to controller synthesis and safety analysis through the development of numerical examples, with emphasis on EU and CVaR. Our contribution is to examine the decision-theoretic, mathematical, and computational trade-offs that arise when using EU and CVaR for optimal control and safety analysis. We are hopeful that this work will advance the interpretability and elucidate the potential benefits of risk-averse control technology.
In this paper, we consider discrete-time partially observed mean-field games with the risk-sensitive optimality criterion. We introduce risk-sensitivity behaviour for each agent via an exponential utility function. In the game model, each agent is we
akly coupled with the rest of the population through its individual cost and state dynamics via the empirical distribution of states. We establish the mean-field equilibrium in the infinite-population limit using the technique of converting the underlying original partially observed stochastic control problem to a fully observed one on the belief space and the dynamic programming principle. Then, we show that the mean-field equilibrium policy, when adopted by each agent, forms an approximate Nash equilibrium for games with sufficiently many agents. We first consider finite-horizon cost function, and then, discuss extension of the result to infinite-horizon cost in the next-to-last section of the paper.
Conditional Value at Risk (CVaR) is a family of coherent risk measures which generalize the traditional mathematical expectation. Widely used in mathematical finance, it is garnering increasing interest in machine learning, e.g., as an alternate appr
oach to regularization, and as a means for ensuring fairness. This paper presents a generalization bound for learning algorithms that minimize the CVaR of the empirical loss. The bound is of PAC-Bayesian type and is guaranteed to be small when the empirical CVaR is small. We achieve this by reducing the problem of estimating CVaR to that of merely estimating an expectation. This then enables us, as a by-product, to obtain concentration inequalities for CVaR even when the random variable in question is unbounded.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
