Multiagent Online Source Seeking Against Nonstochastic Disturbances

This note proposes to leverage the emerging learning techniques to devise a multi-agent online source seeking algorithm under unknown environments. Of particular significance in our problem setups are: i) the underlying environment is not only unknown, but dynamically changing and also perturbed by two types of non-stochastic disturbances; and ii) a group of agents is deployed and expected to cooperatively seek as many sources as possible. Correspondingly, a new technique of discounted Kalman filter is developed to tackle non-stochastic disturbances, and a notion of confidence bound in polytope nature is utilized to aid the computation-efficient cooperation among multiple agents. With standard assumptions on the unknown environment as well as the disturbances, our algorithm is shown to achieve sub-linear regrets under the two types of non-stochastic disturbances; both results are comparable to the state-of-the-art. Numerical examples are provided on a real-world pollution monitoring application to demonstrate the effectiveness of our algorithm.