Intelligent Agents Living in Social Virtual Environments - Bringing Max into Second Life

摘要

When developing cognitive agents capable of interacting with humans, it is often challenging to provide a suitable environment in which agent and user are co-situated. This paper presents a straightforward approach to use Second Life (SL) [1] as a persistent, "near natural", and socially rich environment for research on autonomous agents in complex surroundings, learning social skills, and how they are perceived by humans. In SL, with its registered user base of more than 11 millions, human-human interaction is easily found and technically observable. Moreover it is easy to engage into human-agent interaction and thereby offers a promising way for learning and testing social skills in actual interactions.