Multiagent algorithms often aim to accurately predict the behaviors of other agents and find a best response accordingly. Previous works usually assume an opponent uses a stationary strategy or randomly switches among several stationary ones. However, an opponent may exhibit more sophisticated behaviors by adopting more advanced reasoning strategies, e.g., using a Bayesian reasoning strategy. This paper proposes a novel approach called Bayes-ToMoP which can efficiently detect the strategy of opponents using either stationary or higher-level reasoning strategies. Bayes-ToMoP also supports the detection of previously unseen policies and learning a best-response policy accordingly. We provide a theoretical guarantee of the optimality on detecting the opponent's strategies. We also propose a deep version of Bayes-ToMoP by extending Bayes-ToMoP with DRL techniques. Experimental results show both Bayes-ToMoP and deep Bayes-ToMoP outperform the state-of-the-art approaches when faced with different types of opponents in two-agent competitive games.

No abstract

This paper presents an efficient method to construct white space database for devices to communicate in TV white space (TVWS). The goal is to build a TVWS database which senses the spectrum signal strength from white space devices (WSDs). Considering the incompleteness of measurement data, we formulate the problem of spatial inference as a matrix completion problem and propose a data recovery method by combining a fixed point continuation algorithm (FPCA) with a popular k-nearest neighbor (KNN) algorithm. Simulation results show that the proposed approach has a better performance in the TVWS database recovery than the traditional FPCA.

No abstract

The mitral valve annulus shape is complex but vital for normal functioning mitral apparatus. In this paper, mitral valve annulus curves at different time instances were matched with image intensities as similarity metric. The quality of matching is described by a cost function, involving a predominant term qualifying the matching quality---image intensities. To ensure the smoothness of the solution to the minimization problem, regularization term was added to generate combined cost functional. Numerical simulation results verified the effectiveness of our method.