Safety Verification of Model Based Reinforcement Learning Controllers

2020-10-21 · Akshita Gupta, Inseok Hwang

Model-based reinforcement learning (RL) has emerged as a promising tool for developing controllers for real world systems (e.g., robotics, autonomous driving, etc.). However, real systems often have constraints imposed on their state space which must be satisfied to ensure the safety of the system and its environment. Developing a verification tool for RL algorithms is challenging because the non-linear structure of neural networks impedes analytical verification of such models or controllers. To this end, we present a novel safety verification framework for model-based RL controllers using reachable set analysis. The proposed frame-work can efficiently handle models and controllers which are represented using neural networks. Additionally, if a controller fails to satisfy the safety constraints in general, the proposed framework can also be used to identify the subset of initial states from which the controller can be safely executed.

📄 PDF Abstract BibTeX arXiv:2010.10740

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingmodelModel-based Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning

2021-04-20 · Zikang Xiong, Suresh Jagannathan

There has been significant recent interest in devising verification techniques for learning-enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of interpretability of the neural pol…

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

Joint Differentiable Optimization and Verification for Certified Reinforcement Learning

2022-01-28 · YiXuan Wang, Simon Zhan, Zhilu Wang, Chao Huang 외

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typica…

Bilevel Optimization Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Safe and Reliable Training of Learning-Based Aerospace Controllers

2024-07-09 · Udayan Mandal, Guy Amir, Haoze Wu, Ieva Daukantas 외

In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these models limits their applicability in aerospa…

Deep Reinforcement Learning

Runtime Safety Assurance Using Reinforcement Learning

2020-10-20 · Christopher Lazarus, James G. Lopez, Mykel J. Kochenderfer

The airworthiness and safety of a non-pedigreed autopilot must be verified, but the cost to formally do so can be prohibitive. We can bypass formal verification of non-pedigreed components by incorporating Runtime Safety…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems

2022-10-26 · Yi Dong, Xingyu Zhao, Sen Wang, Xiaowei Huang

Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies.…