2021
DOI: 10.48550/arxiv.2109.08947
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal control

Abstract: We offer a historical overview of methodologies for quantifying the notion of risk and optimizing risk-aware autonomous systems, with emphasis on riskaverse settings in which safety may be critical. We categorize and present stateof-the-art approaches, and we describe connections between such approaches and ideas from the fields of decision theory, operations research, reinforcement learning, and stochastic control. The first part of the review focuses on model-based risk-averse methods. The second part discus… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 107 publications
(242 reference statements)
0
1
0
Order By: Relevance
“…More recent methods include risk-sensitive nonlinear MPC [6,52], Q-learning [44,53], and actor-critic [54,55] methods, for various types of risk measures. Refer to a recent survey [56] for further details. Unlike those methods in which the policy directly optimizes a risk-measure, we propose to instead bias the prediction so that risk-sensitivity can be achieved by a risk-neutral planner that simply optimizes the expected value of the cost.…”
Section: Related Workmentioning
confidence: 99%
“…More recent methods include risk-sensitive nonlinear MPC [6,52], Q-learning [44,53], and actor-critic [54,55] methods, for various types of risk measures. Refer to a recent survey [56] for further details. Unlike those methods in which the policy directly optimizes a risk-measure, we propose to instead bias the prediction so that risk-sensitivity can be achieved by a risk-neutral planner that simply optimizes the expected value of the cost.…”
Section: Related Workmentioning
confidence: 99%