Learning and adaptation are playing important roles in solving numerous complex science and engineering problems, particularly including artificial intelligence, complex system analysis, control engineering, and many multidisciplinary topics. In this respect, some bio-inspired methods, such as reinforcement learning, coevolution learning, and chaos, genetic algorithms, cellular automata, and neural networks, provide essential tools to solve various optimization and control problems of complex systems (e.g., chaotic systems, multiagent systems, and distributed smart grid). This has also stimulated recently increasing research interests and developments on learning and adaptation with particular application to modeling, optimization, and control for complex systems with nonlinear dynamics. Investigating the fundamental properties of bio-inspired learning and adaptation methods (e.g., neural networks, genetic algorithms, and evolutionary game) and showcasing their applications in complex systems (e.g., chaotic systems, social systems, and multiagent systems) could not only promote better understanding of the underlying mechanisms of bio-inspired systems but also provide a possibility to explore their potential to solve complex system behavior analysis, modeling, and control.

This special issue aims at providing a specific opportunity to review the state of the art of this emerging and cross-disciplinary field of bio-inspired learning and adaptation with particular application to complex systems. Authors are invited to present new algorithms, frameworks, software architectures, experiments, and applications aimed at bringing new information about relevant theory and techniques of learning and adaptation. All original papers related to analysis, learning, and adaptation and their application for optimization and control of complex systems are welcome. In particular, we encourage authors to introduce new results for synthesizing learning and optimization into practical complex systems, for example, chaotic systems, smart grid, population systems, multiagent systems, social systems, UAVs, and human-robot interactions.

Potential topics include but are not limited to the following:

• Neural network based learning and adaptation algorithms
• Bio-inspired optimization algorithms including genetic algorithm and particle swarm optimization
• Game theory via advanced adaptation and learning
• Data-driven based optimization of complex systems
• Online/offline policy iteration algorithm and reinforcement learning algorithms
• Distributed learning and optimization methods
• Learning based identification and observer design of complex systems
• Learning based chaotic systems, social systems, and multiagent systems
• Learning and adaptation approaches based on big data
• Learning and adaptation approaches for power and energy engineering
• Learning and adaptation approaches for unmanned vehicles and robotics