Targeted multi-agent communication algorithm based on state control

As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.

Encoding-Decoding-Based Control and Filtering of Networked Systems： Insights, Developments and Opportunities

In order to make the information transmission more efficient and reliable in a digital communication channel with limited capacity, various encoding-decoding techniques have been proposed and widely applied in many branches of the signal processing including digital communications, data compression,information encryption, etc. Recently, due to its promising application potentials in the networked systems(NSs), the analysis and synthesis issues of the NSs under various encoding-decoding schemes have stirred some research attention. However, because of the network-enhanced complexity caused by the limited network resources, it poses new challenges to the design of suitable encoding-decoding procedures to meet certain control or filtering performance for the NSs. In this survey paper, our aim is to present a comprehensive review of the encoding-decodingbased control and filtering problems for different types of NSs.First, some basic introduction with respect to the coding-decoding mechanism is presented in terms of its engineering insights,specific properties and theoretical formulations. Then, the recent representative research progress in the design of the encodingdecoding protocols for various control and filtering problems is discussed. Some possible further research topics are finally outlined for the encoding-decoding-based NSs.

Cooperative Computing Techniques for a Deeply Fused and Heterogeneous Many-Core Processor Architecture

Due to advances in semiconductor techniques, many-core processors have been widely used in high performance computing. However, many applications still cannot be carried out efficiently due to the memory wall, which has become a bottleneck in many-core processors. In this paper, we present a novel heterogeneous many-core processor architecture named deeply fused many-core （DFMC） for high performance computing systems. DFMC integrates management processing ele- ments （MPEs） and computing processing elements （CPEs）, which are heterogeneous processor cores for different application features with a unified ISA （instruction set architecture）, a unified execution model, and share-memory that supports cache coherence. The DFMC processor can alleviate the memory wall problem by combining a series of cooperative computing techniques of CPEs, such as multi-pattern data stream transfer, efficient register-level communication mechanism, and fast hardware synchronization technique. These techniques are able to improve on-chip data reuse and optimize memory access performance. This paper illustrates an implementation of a full system prototype based on FPGA with four MPEs and 256 CPEs. Our experimental results show that the effect of the cooperative computing techniques of CPEs is significant, with DGEMM （double-precision matrix multiplication） achieving an efficiency of 94%, FFT （fast Fourier transform） obtaining a performance of 207 GFLOPS and FDTD （finite-difference time-domain） obtaining a performance of 27 GFLOPS.