Abstract Safe Reinforcement Learning can be defined as the process of learning policies
that maximize the expectation of the return in problems in which it is important to ensure …

More than a decade after the first extensive overview on parameter control, we revisit the
field and present a survey of the state-of-the-art. We briefly summarize the development of …

Federated learning is a distributed machine learning technology that can protect users' data
privacy, so it has attracted more and more attention in the industry and academia …

In their original versions, nature-inspired search algorithms such as evolutionary algorithms
and those based on swarm intelligence, lack a mechanism to deal with the constraints of a …

This is the second edition of our 2003 book. It is primarily a book for lecturers and graduate
and undergraduate students. To this group the book offers a thorough introduction to …

Determination of inspection and maintenance policies for minimizing long-term risks and
costs in deteriorating engineering environments constitutes a complex optimization problem …

This paper provides a comprehensive survey of the most popular constraint-handling
techniques currently used with evolutionary algorithms. We review approaches that go from …

Penalty functions are often used in constrained optimization. However, it is very difficult to
strike the right balance between objective and penalty functions. This paper introduces a …

Engineering design problems are generally large scale or nonlinear or constrained
optimization problems. The Artificial Bee Colony (ABC) algorithm is a successful tool for …

Genetic Algorithms are most directly suited to unconstrained optimization. Application of
Genetic Algorithms to constrained optimization problems is often a challenging effort …