Learning behavior in abstract memory schemes for dynamic optimization problems

Integrating memory into evolutionary algorithms is one major approach to enhance their performance in dynamic environments. An abstract memory scheme has been recently developed for evolutionary algorithms in dynamic environments, where the abstraction of good solutions is stored in the memory instead of good solutions themselves to improve future problem solving. This paper further investigates this abstract memory with a focus on understanding the relationship between learning and memory, which is an important but poorly studied issue for evolutionary algorithms in dynamic environments. The experimental study shows that the abstract memory scheme enables learning processes and hence efficiently improves the performance of evolutionary algorithms in dynamic environments.

[1]  Jürgen Branke,et al.  Evolutionary Optimization in Dynamic Environments , 2001, Genetic Algorithms and Evolutionary Computation.

[2]  Hans-Georg Beyer,et al.  Optimum Tracking with Evolution Strategies , 2006, Evolutionary Computation.

[3]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[4]  Emma Hart,et al.  A Comparison of Dominance Mechanisms and Simple Mutation on Non-stationary Problems , 1998, PPSN.

[5]  Shengxiang Yang,et al.  Associative Memory Scheme for Genetic Algorithms in Dynamic Environments , 2006, EvoWorkshops.

[6]  Chrystopher L. Nehaniv,et al.  Autobiographic agents in dynamic virtual environments - performance comparison for different memory control architectures , 2005, 2005 IEEE Congress on Evolutionary Computation.

[7]  Xin Yao,et al.  Population-Based Incremental Learning With Associative Memory for Dynamic Environments , 2008, IEEE Transactions on Evolutionary Computation.

[8]  Robert Fitch,et al.  Structural Abstraction Experiments in Reinforcement Learning , 2005, Australian Conference on Artificial Intelligence.

[9]  Shengxiang Yang,et al.  Population-based incremental learning with memory scheme for changing environments , 2005, GECCO '05.

[10]  Anabela Simões,et al.  Variable-Size Memory Evolutionary Algorithm to Deal with Dynamic Environments , 2009, EvoWorkshops.

[11]  Hendrik Richter,et al.  A study of dynamic severity in chaotic fitness landscapes , 2005, 2005 IEEE Congress on Evolutionary Computation.

[12]  Ronald W. Morrison,et al.  Designing Evolutionary Algorithms for Dynamic Environments , 2004, Natural Computing Series.

[13]  Amine M. Boumaza.  Learning environment dynamics from self-adaptation: a preliminary investigation , 2005, GECCO '05.

[14]  D. A. Lieberman.  Learning and Memory: An Integrative Approach , 2003 .

[15]  Shengxiang Yang,et al.  A self-organizing random immigrants genetic algorithm for dynamic optimization problems , 2007, Genetic Programming and Evolvable Machines.

[16]  Jürgen Branke,et al.  Evolutionary optimization in uncertain environments-a survey , 2005, IEEE Transactions on Evolutionary Computation.

[17]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[18]  Shengxiang Yang,et al.  Memory Based on Abstraction for Dynamic Fitness Functions , 2008, EvoWorkshops.

[19]  Thomas M. Cover,et al.  Elements of information theory (2. ed.) , 2006 .

[20]  Jürgen Branke,et al.  Memory enhanced evolutionary algorithms for changing optimization problems , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[21]  Peter A. N. Bosman.  Learning and Anticipation in Online Dynamic Optimization , 2007, Evolutionary Computation in Dynamic and Uncertain Environments.

[22]  R.W. Morrison,et al.  Triggered hypermutation revisited , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[23]  Ryszard S. Michalski,et al.  LEARNABLE EVOLUTION MODEL: Evolutionary Processes Guided by Machine Learning , 2004, Machine Learning.

[24]  Jürgen Branke,et al.  A Multi-population Approach to Dynamic Optimization Problems , 2000 .