Backend
Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
arXiv cs.RO0 views
arXiv:2212.06123v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is susceptible to attacks designed either to compromise policy learning or to induce erroneous decisions by trained agents. Although the literature on RL security has grown rapidly and several surveys exist, existing categorizations often fall short in guiding the selection of appropriate defenses for specific systems. In this work, we present a comprehensive survey of 86 recent studies on RL security, addressing these limitations by systematically categorizing attacks and defenses according to defined threat models and single- versus multi-agent settings. Furthermore, we examine the relevance and applicability of state-of-the-art attacks and defense mechanisms within the context of autonomous driving, providing insights to inform the design of robust RL systems.
Source:https://arxiv.org/abs/2212.06123PreviousDailyBrick: Language-Guided Synthesis of Brick Assembly InstructionsNextCurvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration
Related posts
ScreenSpot-Pro on Hugging Face: 0 of 33 Rows Are Verified, and the Top Rows Do Not Share One Test Setting
0dev.to Machine Learning
How Polymarket settles its 5-minute Bitcoin rounds, recomputed in Python
0dev.to Tutorial
Run Private PDF and Image Conversions with I Love Open Converter
0dev.to Tutorial
How to know your linear program's answer is really the best (a product-mix example in Python)
0dev.to Tutorial
How to calculate late payment interest on an unpaid invoice (UK and France, with worked examples)
0dev.to Tutorial

Convert Excel to PDF in Node.js | Export XLSX to PDF Online with REST API
0dev.to Tutorial