Authors:
Mounira Bouzahzah
1
and
Ramdane Maamri
2
Affiliations:
1
University Center of Mila, Algeria
;
2
Mentouri University, Algeria
Keyword(s):
Exception Handling, Learning Agents, Q Learning Algorithm, Reinforcement Learning, Hierarchical Plans.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Distributed and Mobile Software Systems
;
Enterprise Information Systems
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Multi-Agent Systems
;
Software Engineering
;
Symbolic Systems
Abstract:
In this paper we address the problem of exception handling in multi agent systems and we propose an approach based learning agents to provide fault tolerance in multi agent systems. In reality, agents systems are used as a perfect solution to design recent applications that are characterized by being decentralized and dispersed. These systems are subject of errors that occur during execution and that may cause system’s failure; Exceptions are the main cause of the system’s errors. Researchers in fault tolerance field use handling exceptions technique to provide error-prone systems. Through this work, we propose an approach for handling exception using learning agents; this approach assures the most efficient handler for each exception mainly in case of the existence of many handlers and allows the adaptation of decision according to the environment changes. The learning agent is given the capacity to learn about new exceptions from the extern.