paper-with-me

홈 › Papers

Risk-sensitive safety analysis using Conditional Value-at-Risk

2021-01-28 · Margaret P. Chapman, Riccardo Bonalli, Kevin M. Smith, Insoon Yang, Marco Pavone, Claire J. Tomlin

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 via Conditional Value-at-Risk (CVaR). The objective function represents the maximum extent of constraint violation of the state trajectory, averaged over a given percentage of worst cases. This problem is well-motivated but difficult to solve tractably because the temporal decomposition for CVaR is history-dependent. Our primary theoretical contribution is to derive computationally tractable under-approximations to risk-sensitive safe sets. 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 via numerical examples.

📄 PDF Abstract BibTeX arXiv:2101.12086

Code (1)

risk-sensitive-reachability/IEEE-TAC-2021 공식 구현

Similar Papers 제목 키워드 기반

Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback

2023-07-06 · Yu Chen, Yihan Du, Pihe Hu, Siwei Wang 외

Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that employs an Iterated Conditional Value-at-…

Decision MakingLEMMAreinforcement-learningReinforcement Learning (RL)

Risk-sensitive Actor-free Policy via Convex Optimization

2023-06-30 · Ruoqi Zhang, Jens Sjölund

Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensit…

reinforcement-learningReinforcement Learning

Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regression

2025-06-08 · Clinton Enwerem, Aniruddh G. Puranic, John S. Baras, Calin Belta

Mainstream approximate action-value iteration reinforcement learning (RL) algorithms suffer from overestimation bias, leading to suboptimal policies in high-variance stochastic environments. Quantile-based action-value i…

quantile regressionReinforcement Learning (RL)

RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance

2026-06-26 · Shiqiang Gong arxiv

Offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction, making it appealing for safety-critical applications where online exploration is costly or unsafe. Di…

Reinforcement LearningRobot NavigationOffline RL

Risk-Averse Learning with Varying Risk Levels

2025-12-28 · Siyi Wang, Zifan Wang, Karl H. Johansson arxiv

In safety-critical decision-making, the environment may evolve over time, and the learner adjusts its risk level accordingly. This work investigates risk-averse online optimization in dynamic environments with varying ri…