Evolutionary Computation: A Modern Perspective

This is a free online book, currently written/edited by Qiqi Duan @SUSTech (Shenzhen, China) and Yijun Yang @Tencent (Shenzhen, China). We start to write this open book from July, 2023 and plan to finish it in December, 2027. Owing to its open nature, any suggestions, improvements, and corrections to it are highly encouraged via Issues or Pull requests.

Contents (still actively updated)

• Preface
• Terminology
• Introduction to Evolutionary Computation (EC)
  • Motivations from Biological Evolution via Natural Selection: Population-based Diversity and Randomness-based Adaptation
    • Population-based Diversity (versus Convergence)
    • Randomness-based Adaptation (and Self-Adaptation)
    • Fitness-based Selection (Survival-of-the-Fittest versus Extinction)
    • Optimization versus Approximation
  • A Unified Black-Box Optimization Framework from a Statistical Perspective
    • No Free Lunch Theorems for Optimization
    • Exploration-Exploitation Trade-Offs
    • Generality versus Particularity
  • Some Useful and Interesting Applications
    • Open-Source Softwares
      • Python-based Open-Source Softwares
    • Aeronautics&Astronautics
    • Astronomy&Astrophysics
    • Physical Science
    • Chemical Science
    • Environmental and Energy Science
  • Limitations and Possible Risks of Evolutionary Computation
• History of Evolutionary Computation (EC)
  • Early EC Pioneers from 1940s to 1960s
    • Evolutionary Programming (EP)
    • Genetic Algorithms (GA)
    • Evolution Strategies (ES)
  • A Unified Community for Evolutionary Algorithms (EAs) from 1970s to 1990s
  • Theoretical Advances and Practical Considerations from 2000s to 2020s
• Genetic Algorithms (GA)
  • A Computational Model of Adaptation
  • A Popular Algorithm for Discrete Optimization
  • A General-Purpose Searcher for Unstructured Problems
  • Some Representative Applications of GA
• Evolution Strategies (ES)
  • Self-Adaptation and Covariance Matrix Adaptation ES (CMA-ES)
  • Natural Gradients and Natural ES (NES)
  • Gradient Estimation (OpenAI-ES) and Variance Reduction (Persistent ES)
  • Meta-ES and Distributed ES (DES)
  • Typical Optimization Applications of ES
• Genetic Programming (GP)
• NeuroEvolution
  • NeuroEvolution of Augmenting Topologies (NEAT)
  • Population-Based Training (PBT)
• Parallel/Distributed Evolutionary Computation
• Evolutionary Robotics (ER) and Quality-Diversity (QD)
• Evolutionary Reinforcement Learning (ERL)
• Evolutionary Meta-Learning (EML)
• Learning and Evolution
• Search-Based Software Engineering
• Swarm Intelligence
  • Ant Colony Optimization
  • Particle Swarm Optimization
  • Swarm Robotics