Multilevel Modeling of Dialogue Environment for e-Commerce Agents
Wojciech Jamroga, Waldzinski, D. · 2001
this paper. When the agent's knowledge on the most specific (and useful) level turns out to be insufficient or inaccurate, he can always use some knowledge of a more general kind. 1. VIRTUAL AGENT'S REALITY A virtual agent lives in a world, which consists of both virtual and 'real' components. The world, together with the agent's own goals and capabilities, constitute the reality the agent has to cope with. The agent interacts with the reality, trying to fulfill his (implicit or explicit) goals. Thus, it's good for the agent to learn some (implicit or explicit) model of the reality to adjust future actions to the predicted response of the environment. The agent may perceive the environment as a unity - this approach pays off especially when the environment consists only of passive elements. Even in worlds (possibly) inhabited by other agents, it may be a good solution, as reported in (Sen & Sekaran 1998) for block pushing agents using a very simple reinforcement le