TY - GEN
T1 - A Reinforcement Learning Approach to Design Verification Strategies of Engineered Systems
AU - Xu, Peng
AU - Salado, Alejandro
AU - Xie, Guangrui
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/11
Y1 - 2020/10/11
N2 - System verification is a critical process in the development of engineered systems. Engineers gain confidence in the correct functionality of the system before it is deployed into operation by executing verification activities. Choosing the right set of verification activities at the right system development stage, that is, designing a verification strategy (VS), is essential to balancing information discovery and verification cost. Only recently, quantitative methods have been proposed to support the design of verification strategies. However, their applicability in real-life scenarios is impractical due to their limited computational efficiency in the high dimensional solution space of the VS selection problem. This paper presents a reinforcement learning (RL) approach to search for a near-optimal VS. Specifically, the VS design problem is formulated as a Markov decision process (MDP) in which a value function is required. Then we combine tree search and a neural network (NN) to design a RL algorithm. In the RL algorithm, the value function is approximated as a NN that is trained in an iterative way. The near-optimal VS can be generated from the trained NN. A case study is presented to show the superiority of the proposed method.
AB - System verification is a critical process in the development of engineered systems. Engineers gain confidence in the correct functionality of the system before it is deployed into operation by executing verification activities. Choosing the right set of verification activities at the right system development stage, that is, designing a verification strategy (VS), is essential to balancing information discovery and verification cost. Only recently, quantitative methods have been proposed to support the design of verification strategies. However, their applicability in real-life scenarios is impractical due to their limited computational efficiency in the high dimensional solution space of the VS selection problem. This paper presents a reinforcement learning (RL) approach to search for a near-optimal VS. Specifically, the VS design problem is formulated as a Markov decision process (MDP) in which a value function is required. Then we combine tree search and a neural network (NN) to design a RL algorithm. In the RL algorithm, the value function is approximated as a NN that is trained in an iterative way. The near-optimal VS can be generated from the trained NN. A case study is presented to show the superiority of the proposed method.
KW - Markov decision process
KW - System verification
KW - reinforcement learning
KW - verification strategy
UR - http://www.scopus.com/inward/record.url?scp=85098845478&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098845478&partnerID=8YFLogxK
U2 - 10.1109/SMC42975.2020.9282929
DO - 10.1109/SMC42975.2020.9282929
M3 - Conference contribution
AN - SCOPUS:85098845478
T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
SP - 3543
EP - 3550
BT - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Y2 - 11 October 2020 through 14 October 2020
ER -