Constructing Robust Conversation Policies in Dynamic Agent Communities

Conversation policies codify the allowable exchanges of speech acts among agents as they execute specific types of tasks. Both the set of agents in a community, and the nature of those agents may change over time, making it necessary for agents to conform to a common set of conversation policies and for those conversations to be robust to change and failure. In this paper, we describe aspects of the implementation of conversation policies in InfoSleuth, including the integral use of finite-state automata for defining those policies. We identify features of those automata and the underlying performatives that are necessary for the robust and correct execution of these policies in an operational community. In several cases, more complex conversations are built using simpler underlying components. We describe the construction of new conversation policies from these components using two mechanisms, extension and concatenation. In this way, we can ensure that the specification of these...

• Type: Conference
• Year: 2000
• Where: AGENTCL
• Authors: Marian H. Nodine, Amy Unruh
• Keywords: AGENTCL 2000, Allowable Exchanges, Conversation Policies, Intelligent Agents, Multiple Conversation Policies