Pareto Optimality in Coevolutionary Learning
نویسندگان
چکیده
We develop a novel coevolutionary algorithm based upon the concept of Pareto optimality. The Pareto criterion is core to conventional multi-objective optimization (MOO) algorithms. We can think of agents in a coevolutionary system as performing MOO, as well: An agent interacts with many other agents, each of which can be regarded as an objective for optimization. We adapt the Pareto concept to allow agents to follow gradient and create gradient for others to follow, such that coevolutionary learning succeeds. We demonstrate our Pareto coevolution methodology with the majority function, a density classification task for cellular automata.
منابع مشابه
Low-Area/Low-Power CMOS Op-Amps Design Based on Total Optimality Index Using Reinforcement Learning Approach
This paper presents the application of reinforcement learning in automatic analog IC design. In this work, the Multi-Objective approach by Learning Automata is evaluated for accommodating required functionalities and performance specifications considering optimal minimizing of MOSFETs area and power consumption for two famous CMOS op-amps. The results show the ability of the proposed method to ...
متن کاملOptimality conditions for Pareto efficiency and proper ideal point in set-valued nonsmooth vector optimization using contingent cone
In this paper, we first present a new important property for Bouligand tangent cone (contingent cone) of a star-shaped set. We then establish optimality conditions for Pareto minima and proper ideal efficiencies in nonsmooth vector optimization problems by means of Bouligand tangent cone of image set, where the objective is generalized cone convex set-valued map, in general real normed spaces.
متن کاملSolution of Multi-Objective optimal reactive power dispatch using pareto optimality particle swarm optimization method
For multi-objective optimal reactive power dispatch (MORPD), a new approach is proposed where simultaneous minimization of the active power transmission loss, the bus voltage deviation and the voltage stability index of a power system are achieved. Optimal settings of continuous and discrete control variables (e.g. generator voltages, tap positions of tap changing transformers and the number of...
متن کاملPERFORMANCE-BASED MULTI-OBJECTIVE OPTIMUM DESIGN FOR STEEL STRUCTURES WITH INTELLIGENCE ALGORITHMS
A multi-objective heuristic particle swarm optimiser (MOHPSO) based on Pareto multi-objective theory is proposed to solve multi-objective optimality problems. The optimality objectives are the roof displacement and structure weight. Two types of structure are analysed in this paper, a truss structure and a framework structure. Performance-based seismic analysis, such as classical and modal push...
متن کاملAnytime Self-play Learning to Satisfy Functional Optimality Criteria
We present an anytime multiagent learning approach to satisfy any given optimality criterion in repeated game self-play. Our approach is opposed to classical learning approaches for repeated games: namely, learning of equilibrium, Pareto-efficient learning, and their variants. The comparison is given from a practical (or engineering) standpoint, i.e., from a point of view of a multiagent system...
متن کامل