Making Agents Less Annoying: towards an Animated Agent That Responds to Social Cues
نویسنده
چکیده
Animated interface agents have been proposed as a more natural way for the user to interact with computers. Such agents are frequently used in pedagogical and program help applications. While many aspects of social agents have been investigated, that of keeping an appropriate social distance seems to have been overlooked. This ability is coupled with an understanding of when advice is and is not wanted. An agent that gives advice in an Othello program is implemented, which using reinforcement learning adapts its frequency of suggestions to whether or not the user takes the advice. The amount of suggestions that the user can expect is visualized for the user by agent size and position. This agent is compared to one which always gives advice. In the evaluation, test participants experienced that the first agent adapted to their behavior and also found it less distracting.
منابع مشابه
Designing and Evaluating Animated Agents as Social Actors
Recent years have witnessed a growing interest in employing animated agents for tasks that are typically performed by humans. They serve as communicative partners in a variety of applications, such as tutoring systems, sales, or entertainment. This paper first discusses design principles for animated agents to enhance their effectiveness as tutors, sales persons, or actors, among other roles. I...
متن کاملTowards Personalities for Animated Agents with Reactive and Planning Behaviors
We describe a framework for creating animated simulations of virtual human agents. The framework allows us to capture flexible patterns of activity, reactivity to a changing environment, and certain aspects of an agent personality model. Each leads to variation in how an animated simulation will be realized. As different parts of an activity make different demands oil an agent's resources and d...
متن کاملDesigning Animated Agents as Social Actors and Dramatis Personae for Web-based Interaction
Recent years have witnessed a growing interest in employing animated agents for tasks that are typically performed by humans. They serve as communicative partners in a variety of applications, such as tutoring systems, sales, or entertainment. This paper discusses design principles for animated agents to enhance their effectiveness as tutors, sales persons, or actors, among other roles. It is a...
متن کاملUsing Inverse Planning and Theory of Mind for Social Goal Inference
Previous research shows that people assign latent goals or intentions to simple animated agents based on the motion behavior of these agents. We propose that human observers can infer that an animated agent has a partial state of belief about its environment and that observers use this information – in combination with the agent's observable behavior – to infer its goals. We conducted an experi...
متن کاملAnimated Agents for Language Conversation Training
Animated agents are cartoon-style characters that facilitate the learning process. We take an animated agent approach to improve English conversation skills of Japanese students. In particular, we use animated agents as conversational partners in interactive role-playing environments (theater, drama, and games). In order to engage the language student, animated agents feature believability-enha...
متن کامل