Reactive Search Optimization

Reactive Search Optimization (RSO) advocates the integration of sub-symbolic machine learning techniques into search heuristics for solving complex optimization problems. The word reactive hints at a ready response to events during the search through an internal online feedback loop for the self-tuning of critical parameters.
Methodologies of interest for Reactive Search include machine learning and statistics, in particular reinforcement learning, active or query learning, neural networks, and meta-heuristics (although the boundary signalled by the "meta" prefix is not always clear).

Intelligent optimization, a superset of Reactive Search, refers to a more extended area of research, including online and offline schemes based on the use of memory, adaptation, incremental development of models, experimental algorithmics applied to optimization, intelligent tuning and design of heuristics.

This site supports a virtual community of academic and industrial researchers and developers interested in Reactive Search, and includes:

• A description of the technique and of the underlying concepts
• A mailing list to send news, and a Reactive Search community which you can joint if interested in reactive topics.
• A list of people, institutions and other resources
• A list of some applications developed in the world
• A bibliography of research and implementation papers
• The new book about "Reactive Search and Intelligent Optimization"
• A vintage '96 position paper on "Machine learning methods for parameter tuning in heuristics"
• Online and offline Software tools implementing Reactive Search methods.

---

	LION 4, Learning and Intelligent OptimizatioN, Venice - Italy, Jan 18-22 2010, Photos of LION4 (courtesy pf Carlo Nicolini)
	Reactive Search and Intelligent Optimization, by Roberto Battiti, Mauro Brunato and Franco Mascia