The Self-Adaptive Context Learning Pattern: Overview and Proposal

Abstract

OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible. This is an author-deposited version published in : http://oatao.univ-toulouse.fr/ Eprints ID : 15394The contribution was presented at CONTEXT 2015 :http://cyprusconferences.org/context2015/ Abstract. Over the years, our research group has designed and developed many self-adaptive multi-agent systems to tackle real-world complex problems, such as robot control and heat engine optimization. A recurrent key feature of these systems is the ability to learn how to handle the context they are plunged in, in other words to map the current state of their perceptions to actions and effects. This paper presents the pattern enabling the dynamic and interactive learning of the mapping between context and actions by our multi-agent systems.

Self-organizing multi-agent systems for the control of complex systems

“…Other AMASs have tackled the problem of learning and control with similar Context Agents, for instance with model generation ( Nigon et al, 2016 ) and ambient robotics ( Verstaevel et al, 2016 ). Context Agents are being generalized and standardized to become a pattern for context learning in a multi-agent system ( Boes et al, 2015 ).…”

Principles and experimentations of self-organizing embedded agents allowing learning from demonstration in ambient robotics

“…At last, we want both to formalize our approach and to compare its performances with other well-known learning techniques. Formalization has already led to a proposal of a generic pattern for context learning with Context agents [34].…”

Lifelong Machine Learning with Adaptive Multi-Agent Systems

“…In these applications, a set of distributed agents locally learns and exploits a model of an agent behavior from the interactions between the agent and its environment. On the next section, we present the Self-Adaptive Context Pattern (Boes et al, 2015), our proposal to design agents with lifelong learning capacities.…”

“…The pattern has been applied to various problems where learning is a way toward self-organisation ( Boes et al, 2015). In each of those problems, the recurrent key feature is to learn a model of the interactions between the agent and its environment by extracting the context in which those actions are performed and associating information about this context in order to lately use this information to behave well.…”