Learning by Observation in Software Agents

2004

This paper presents several design principles used in the development of the Disciple learning agents. The process of developing such an agent relies on importing ontologies from existing knowledge repositories, and on teaching the agent how to perform various tasks, in a way that resembles how an expert would teach a human apprentice when solving problems in cooperation. Experimental results support the usefulness of the presented principles which may be useful for the development of other agents.

Ibm Systems Journal, 1996

Agent software is a topic of growing interest to users and developers in the computer industry. Already, agents and wizards help users automate tasks such as editing and searching for information. But just as we expect human assistants to learn as we work with them, we will also come to expect our computer agents to learn from us. This paper explores the idea of an instructible agent that can learn both from examples and from advice. To understand design issues and languages for human-agent communication, we first describe an experiment that simulates the behavior ofsuch an agent. Then we describe some implemented and ongoing instructible agent projects in text and graphic editing, World Wide Web browsing, and virtual reality. Finally, we analyze the trade-offs involved in agent software and argue that instructible agents represent a "sweet spot" in the trade-off between convenience and control.

Lecture Notes in Computer Science, 2005

During the last years, Intelligent Virtual Environments for Training have become a quite popular application of computer science to education. These systems involve very different technologies, ranging from computer graphics to artificial intelligence. However, little attention has been paid to software engineering issues, and most of these systems are developed in an ad-hoc way that does not allow the reuse of their components or even an easy modification of the application. We describe an agent-based software architecture that is intended to be easily extended and modified. Also, some experiments to test the suitability of the architecture are shown.

Applied Artificial Intelligence, 2005

This paper discusses Betty's Brain, a teachable agent in the domain of river ecosystems that combines learning by teaching with self-regulation mentoring to promote deep learning and understanding. Two studies demonstrate the effectiveness of this system. The first study focused on components that define student-teacher interactions in the learning by teaching task. The second study examined the value of adding meta-cognitive strategies that governed Betty's behavior and self-regulation hints provided by a mentor agent. The study compared three versions: a system where the student was tutored by a pedagogical agent (ITS), a learning by teaching system (LBT) , where students taught a baseline version of Betty, and received tutoring help from the mentor, and a learning by teaching system (SRL), where Betty was enhanced to include self-regulation strategies, and the mentor provided help on domain material plus how to become better learners and better teachers. Results indicate that the addition of the self-regulated Betty and the self-regulation mentor better prepared students to learn new concepts later, even when they no longer had access to the SRL environment. 4 TAG-V: The Teachable Agents Group at Vanderbilt: Members of this group who contributed to this work include From a learning system viewpoint, a multi-agent architecture was developed to overcome drawbacks of the previous version of Betty's Brain, and to introduce the new features to promote inquiry based self-regulated learning that we have discussed above. The software system was redesigned to modularize the various functions required in the system, and to systematically introduce the notion of interactions among the agents .

1997

This paper describes a software agent that learns procedural knowledge from a human instructor well enough to teach human students. In order to teach, the agent needs more than the ability to perform a procedure. It must also be able to monitor human students performing the procedure and be able to articulate the reasons why actions are necessary. Our research concentrates on helping an instructor instruct the agent in a natural manner, on reducing the burden on the instructor, and on focusing learning on the procedure being taught. Initially the agent has little domain knowledge. The instructor demonstrates a procedure by directly manipulating a simulated environment. However, one demonstration is not sufficient for understanding the causal relationships between a demonstration's actions. Unfortunately, the more demonstrations a procedure requires, the greater the instructor's burden. However, fewer demonstrations can be required if the agent autonomously experiments. Our experiments attempt to understand the causal dependencies between a demonstration's actions by perturbing the order of the demonstration's actions.

Lecture Notes in Computer Science, 2014

This paper presents an agent based approach to knowledge representation and learning methods. Agent architecture is described and discussed, together with its advantages and limitations. Main purpose of the proposed approach is to gain further insight in current teaching methods with a foremost aspiration for their improvement. Two different experimental studies were conducted; the first one addressing knowledge representation and the second one regarding knowledge transfer between agents. Obtained results are presented and analysed.

International Series in Intelligent Technologies, 2000

This chapter introduces the concept of intelligent agent, analyses some of the issues and trends in developing them and presents a specific agent development approach. The presented approach, called Disciple, relies on importing ontologies from existing repositories of knowledge, and on teaching the agent how to perform various tasks, in a way that resembles how an expert would teach a human apprentice when solving problems in cooperation.

Proceedings of The …, 1998

This paper describes the\ conscious" learning mechanism of an adaptive software agent, Conscious Mattie (CMattie). This conscious software agent takes the role of a departmental seminar organizer. The agent gathers seminar information via email from humans, composes an announcement of the next week's seminars, and mails it to members of a mailing list which she maintains. Through further interaction with seminar organizers, CMattie learns to handle new variations of seminars, such as colloquia. In this paper, the ...

2003

ABSTRACT. Cognitive Agent communication is a research field in full development. We propose here an extension and an implementation of the STROBE model, which regards the Agents as Scheme interpreters. These Agents are able to interpret messages in a dedicated environment including an interpreter that learns from the current conversation. These interpreters evolve dynamically, progressively with the conversations, and thus represent evolving meta level Agent knowledge.

Working Notes of AAAI-97 Workshop on Multiagent …, 1997

Agents Learning about Agents: A Framework and Analysis. Jose M. Vidal and Edmund H. Durfee. We provide a framework for the study of learning in certain types of multi-agent systems (MAS), that divides an agent's knowledge about others into different utypes. ...