Cooperative formation control of unmanned ground vehicles (UGVs) has become one the important research hotspots in application UGV and attracted more attention military civil fields. Compared with traditional algorithms, reinforcement-learning-based algorithms can provide a new solution lower complexity for real-time by equipping UGVs artificial intelligence. Therefore, this paper, distributed ...

Air supply system is an important subsystem in a PEMFC engine system. Research on the control strategy of air great importance and significance engineering. In this paper intelligent controller based distributed deep reinforcement learning which exerts better over flux proton exchange membrane fuel cell (PEMFC) proposed. addition, collective intelligence exploration multi-delay deterministic po...

In this paper, user set selection in the allocation sequences of round-robin (RR) scheduling for distributed antenna transmission with block diagonalization (BD) pre-coding is proposed. prior research, initial phase equipment RR has been investigated. The performance proposed inferior to that proportional fair (PF) under severe intra-cell interference. multi-input multi-output technology BD app...

In this paper, a new voltage cooperative control strategy for distributed power generation system is proposed based on the multi-agent advantage actor-critic (MA2C) algorithm, which realizes flexible management and effective of energy. The attentional message processor (AACMP) extended into MA2C method to select important messages from all communication adaptively process efficiently. trained b...

In this paper, the problem of minimizing weighted sum age information (AoI) and total energy consumption Internet Things (IoT) devices is studied. considered model, each IoT device monitors a physical process that follows nonlinear dynamics. As dynamics vary over time, should find an optimal sampling frequency to sample real-time system send sampled base station (BS). Due limited wireless resou...

This paper describes multi-agent learning experiments performed on tactical sequences of the pursuit evasion game on very small grids. It underlines the performance difference between a centralized approach and a distributed approach when using Rmax, a model-based reinforcement learning algorithm. The prey’s goal is to go out of the grid and the predators’ goal is to kill the prey. The prey may...

Graph optimization problems (such as minimum vertex cover, maximum cut, traveling salesman problems) appear in many fields including social sciences, power systems, chemistry, and bioinformatics. Recently, deep reinforcement learning (DRL) has shown success automatically good heuristics to solve graph problems. However, the existing RL systems either do not support environments or multiple GPUs...

Balancing load in cloud based is an important aspect that plays a vital role order to achieve sharing of between different types resources such as virtual machines lay on servers, storage the form hard drives and servers. Reinforcement learning approaches can be adopted with computing quality service factors minimized cost response time, increased throughput, fault tolerance utilization all ava...