Search

• A combination of Deep Q-Learning algorithm and metaheuristic GSA is offered. • GSA initializes the weights and the biases of the neural networks. • A comparison with classical random, metaheuristic PSO and GWO is carried out. • The validation is done on real-time nonlinear servo system position control. • The drawbacks of randomly initialized neural networks are mitigated. This paper presents a novel Reinforcement Learning (RL)-based control approach that uses a combination of a Deep Q-Learning (DQL) algorithm and a metaheuristic Gravitational Search Algorithm (GSA). The GSA is employed to initialize the weights and the biases of the Neural Network (NN) involved in DQL in order to avoid the instability, which is the main drawback of the traditional randomly initialized NNs. The quality of a particular set of weights and biases is measured at each iteration of the GSA-based initialization using a fitness function aiming to achieve the predefined optimal control or learning objective. The data generated during the RL process is used in training a NN-based controller that will be able to autonomously achieve the optimal reference tracking control objective. The proposed approach is compared with other similar techniques which use different algorithms in the initialization step, namely the traditional random algorithm, the Grey Wolf Optimizer algorithm, and the Particle Swarm Optimization algorithm. The NN-based controllers based on each of these techniques are compared using performance indices specific to optimal control as settling time, rise time, peak time, overshoot, and minimum cost function value. Real-time experiments are conducted in order to validate and test the proposed new approach in the framework of the optimal reference tracking control of a nonlinear position servo system. The experimental results show the superiority of this approach versus the other three competing approaches. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a new bare-bones multi-objective particle swarm optimization algorithm to solve the environmental/economic dispatch problems. The algorithm has three distinctive features: a particle updating strategy which does not require tuning up control parameters; a mutation operator with action range varying over time to expand the search capability; and an approach based on particle diversity to update the global particle leaders. Several trials have been carried out on the IEEE 30-bus test system. By comparing with seven existing multi-objective optimization algorithms and three well-known multi-objective particle swarm optimization techniques, it is found that our algorithm is capable of generating excellent approximation of the true Pareto front and can be used to solve other types of multi-objective optimization problems. [Copyright &y& Elsevier]

Abstract: This paper presents a novel framework of the estimation of particle swarm distribution algorithms (EPSDAs). The aim is to effectively combine particle swarm optimization (PSO) with the estimation of distribution algorithms (EDAs) without losing their unique features. This aim is achieved by incorporating the following mechanisms: (1) selection is applied to the local best solutions in order to obtain more promising individuals for model building, (2) a probabilistic model of the problem is built from the selected solutions, and (3) new individuals are generated by a stochastic combination of the EDA’s model sampling method and the PSO’s particle moving mechanism. To exhibit the utility of the EPSDA framework, an extended compact particle swarm optimization (EcPSO) is developed by combining the strengths of the extended compact genetic algorithm (EcGA) with binary PSO (BPSO), along the lines of the suggested framework. Due to its effective nature of harmonizing the global search of EcGA with the local search of BPSO, EcPSO is able to discover the optimal solution in a fast and reliable manner. Experimental results on artificial to real-world problems have adduced grounds for the effectiveness of the proposed approach. [Copyright &y& Elsevier]

Abstract: Global optimization of high-dimensional problems in practical applications remains a major challenge to the research community of evolutionary computation. The weakness of randomization-based evolutionary algorithms in searching high-dimensional spaces is demonstrated in this paper. A new strategy, SP-UCI is developed to treat complexity caused by high dimensionalities. This strategy features a slope-based searching kernel and a scheme of maintaining the particle population’s capability of searching over the full search space. Examinations of this strategy on a suite of sophisticated composition benchmark functions demonstrate that SP-UCI surpasses two popular algorithms, particle swarm optimizer (PSO) and differential evolution (DE), on high-dimensional problems. Experimental results also corroborate the argument that, in high-dimensional optimization, only problems with well-formative fitness landscapes are solvable, and slope-based schemes are preferable to randomization-based ones. [Copyright &y& Elsevier]