DeepAI AI Chat
Log In Sign Up

Learning adaptive differential evolution algorithm from optimization experiences by policy gradient

by   Jianyong Sun, et al.

Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and associated control parameters. However, the determination process for the most suitable parameter setting is troublesome and time-consuming. Adaptive control parameter methods that can adapt to problem landscape and optimization environment are more preferable than fixed parameter settings. This paper proposes a novel adaptive parameter control approach based on learning from the optimization experiences over a set of problems. In the approach, the parameter control is modeled as a finite-horizon Markov decision process. A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i.e. parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure. The differential evolution algorithm based on the learned agent is compared against nine well-known evolutionary algorithms on the CEC'13 and CEC'17 test suites. Experimental results show that the proposed algorithm performs competitively against these compared algorithms on the test suites.


On Hyper-parameter Tuning for Stochastic Optimization Algorithms

This paper proposes the first-ever algorithmic framework for tuning hype...

Deep Reinforcement Learning Based Parameter Control in Differential Evolution

Adaptive Operator Selection (AOS) is an approach that controls discrete ...

Evolutionary optimization of an experimental apparatus

In recent decades, cold atom experiments have become increasingly comple...

Distributed Evolution Strategies for Black-box Stochastic Optimization

This work concerns the evolutionary approaches to distributed stochastic...

Recurrent Network-based Deterministic Policy Gradient for Solving Bipedal Walking Challenge on Rugged Terrains

This paper presents the learning algorithm based on the Recurrent Networ...

Analyzing Adaptive Parameter Landscapes in Parameter Adaptation Methods for Differential Evolution

Since the scale factor and the crossover rate significantly influence th...