Classical Risk-Averse Control for a Finite-Horizon Borel Model

2021-07-29 · Margaret P. Chapman, Kevin M. Smith

We study a risk-averse optimal control problem for a finite-horizon Borel model, where a cumulative cost is assessed via exponential utility. The setting permits non-linear dynamics, non-quadratic costs, and continuous state and control spaces but is less general than the problem of optimizing an expected utility. Our contribution is to show the existence of an optimal risk-averse controller without using state space augmentation and therefore offer a simpler solution method from first principles compared to what is currently available in the literature.

📄 PDF Abstract BibTeX arXiv:2107.13981

Code (0)

등록된 구현이 없습니다.

CVaR-based Safety Analysis in the Infinite Time Horizon Setting

2021-08-15 · Chuanning Wei, Michael Fauss, Margaret P. Chapman

We develop a risk-averse safety analysis method for stochastic systems on discrete infinite time horizons. Our method quantifies the notion of risk for a control system in terms of the severity of a harmful random outcom…

Management

Risk-Averse Reinforcement Learning via Dynamic Time-Consistent Risk Measures

2023-01-14 · Xian Yu, Siqian Shen

Traditional reinforcement learning (RL) aims to maximize the expected total reward, while the risk of uncertain outcomes needs to be controlled to ensure reliable performance in a risk-averse setting. In this paper, we c…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

2020-04-22 · Shangtong Zhang, Bo Liu, Shimon Whiteson

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in tha…

MuJoCo reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk

2022-09-09 · Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh, Reazul Russel

Prior work on safe Reinforcement Learning (RL) has studied risk-aversion to randomness in dynamics (aleatory) and to model uncertainty (epistemic) in isolation. We propose and analyze a new framework to jointly model the…

Reinforcement Learning (RL)Safe Reinforcement Learning

Risk-Averse Receding Horizon Motion Planning for Obstacle Avoidance using Coherent Risk Measures

2022-04-20 · Anushri Dixit, Mohamadreza Ahmadi, Joel W. Burdick

This paper studies the problem of risk-averse receding horizon motion planning for agents with uncertain dynamics, in the presence of stochastic, dynamic obstacles. We propose a model predictive control (MPC) scheme that…

Model Predictive Control Motion Planning