Multiagent Coordination Optimization Research Articles

Dynamic Coordination-Based Reinforcement Learning for Driving Policy

With the development of communication technology and artificial intelligence technology, intelligent vehicle has become a very important part of Internet of Things technology. At present, the single-vehicle intelligence is gradually improved, and more and more unmanned vehicles appear on the road. In the future, these individual intelligence applications need to be transformed into collective intelligence to give full play to the greater advantages of unmanned driving. For example, individual intelligence is self-interest. If there is no collective cooperation, it may affect the whole traffic flow for its own speed. Although the vehicle ad hoc network technology provides a guarantee for the communication between vehicles and makes cooperation between vehicles possible, there are still challenges in how to adapt to coordination learning. Coordination reinforcement learning is one of the most promising methods to solve the multiagent coordination optimization problems. However, existing coordinative learning approaches that usually rely on static topologies cannot be easily adopted to solve the vehicle coordination problems in the dynamic environment. We propose a dynamic coordination reinforcement learning to help vehicles make their driving decisions. First, we apply driving safety field theory to construct the dynamic coordination graph (DCG), representing the dynamic coordination behaviors among vehicles. Second, we design reinforcement learning techniques on our DCG model to implement the joint optimal action reasoning for the multivehicle system and eventually derive the optimal driving policy for each vehicle. Finally, compared with other multiagent learning methods, our method has a significant improvement in security and speed, which is about 1% higher than other multiagent learning methods, but its training speed is also significantly improved about 8%.

A hybrid multi-agent Coordination Optimization Algorithm

Abstract Many-Objective optimization problems (MaOPs) are the optimization problems which contain more than three conflicting objectives. Extensive interests from both algorithms development and practical applications are attracted to study the MaOPs. The success of the Particle Swarm Optimization (PSO) algorithm and Evolutionary Algorithm (EA) as single-objective optimizers motivated researchers to extend the use of those techniques to solve the MaOPs: many-objective particle swarm optimization algorithms (MOPSOs) and many-objective evolutionary algorithms (MOEAs). In this paper, we extend a recently developed bio-inspired optimization algorithm, Multi-agent Coordination Optimization Algorithm (MCO) from a single-objective optimizer to a many-objective optimizer: Many-Objective Multi-agent Coordination Optimization Algorithm (MOMCO). The cooperative mechanism in the MCO accelerates the searching process. To tackle the MaOPs, an inverted generational distance indicator method is used to distinguish the non-dominated solutions in MOMCO to balance the diversity ability and convergence ability of the solutions during the searching process. Together with a hybrid combination with EA, the diversity and accuracy of the MOMCO will be improved. Moreover, the convergence issue is studied for the proposed MOMCO algorithm by using the Jury's test. Experimental results are provided to demonstrate the effectiveness of the proposed MOMCO by comprising with six state-of-the-art MOPSOs and MOEAs. By calculating the Wilcoxon's rank sum test, the proposed MOMCO algorithm demonstrated superior performance among all the seven algorithms.

Parallel Multiagent Coordination Optimization Algorithm: Implementation, Evaluation, and Applications

In this paper, a parallel computing implementation of a multiagent coordination optimization (MCO) algorithm is introduced using $\mathtt {parfor}$ , a built-in MATLAB function. As a novel variation of particle swarm optimization (PSO), the MCO algorithm has demonstrated significant performance improvement, in terms of both accuracy and efficiency, in solving real-time optimization problems when compared with PSO. However, the ability to handle large-scale optimization problems or use more particles in the algorithm is limited by the sequential implementation of the original MCO algorithm. A numerical evaluation of the parallel MCO algorithm was conducted using the supercomputers in the High Performance Computing Center at Texas Tech University. Based on the results of this evaluation, it was determined that the performance of the parallel MCO is not only superior to that of PSO but is highly efficient as it reduces the computational time. The parallel binary MCO (BMCO) algorithm is presented here as well. By combining the parallel MCO with parallel BMCO algorithms, a new parallel mixed-binary nonlinear programming MCO solver is proposed. Finally, a load balancing coordination problem, a multiagent formation control problem, and a power system vulnerability analysis problem are solved using the corresponding parallel MCO algorithm.

Optimal Balanced Coordinated Network Resource Allocation Using Swarm Optimization

In this paper, we present a new control-theoretic framework to efficiently design balanced coordinated resource allocation algorithms in a network based on semistabilization theory for discrete-time stochastic linear systems together with compartmental modeling. Specifically, necessary and sufficient conditions for equivalent, control-theoretic characterizations of the proposed balanced coordinated resource allocation design problem are derived, which are based on a new notion of semiobservability and a new semistable Lyapunov equation. With this theory, we first unveil a striking connection between the balanced coordinated network resource allocation design problem and optimal semistable control theory by means of a stochastic optimal semistable control technique. Then we convert this optimal control-based design problem into a constrained, nonlinear optimization problem to look for possible numerical solutions to the original balanced coordinated resource allocation algorithm design problem. To this end, we propose a class of randomized swarm optimization-based numerical algorithms called multiagent coordination optimization to solve the constrained, nonlinear optimization problem. Finally, numerical results are provided to validate the proposed design framework and an application of a target search problem for threat detection and resource allocation is presented to further show the effectiveness of the proposed approach.