Anomaly Detection Under Controlled Sensing Using Actor-Critic Reinforcement Learning

We consider the problem of detecting anomalies among a given set of processes using their noisy binary sensor measurements. The noiseless sensor measurement corresponding to a normal process is 1, and the measurement is 0 if the process is anomalous. The decision-making algorithm has no knowledge of the number of anomalous processes. The algorithm is allowed to choose a subset of the sensors at each time instant until the confidence level on the decision exceeds the desired value. Our objective is to design a sequential sensor selection policy that dynamically determines which processes to observe at each time and when to terminate the search. The selection policy is designed such that the anomalous processes are detected with a minimum cost which comprises the delay in detection and the cost of sensing. We cast this problem as a sequential hypothesis testing problem within the framework of Markov decision processes, and solve it using the actor-critic deep reinforcement learning algorithm. This deep neural network-based algorithm offers a low complexity solution with good detection accuracy. We also study the effect of dependence between the processes on the algorithm performance. Through numerical experiments, we show that our algorithm is able to adapt according to any unknown correlation pattern of the processes.