Research in interactive learning encompasses a wide range of approaches and is referenced under many names, including teachable agents, imitation, learning from demonstration, active learning, interactive shaping, and bootstrapped learning.  This workshop aims to advance research in interactive learning by bringing together researchers with different approaches and attempting to establish standards for comparing systems, evaluating their performance, and combining results from different aspects of the problem.

The potential application domains for interactive learning are many — both for embodied and for virtual agents — and range across a spectrum of abstractness from fine motor skills to deep abstract knowledge such as that acquired at a university.  An interactive learning system therefore may be formulated in a variety of ways, and we encourage a broad spectrum of applications.  In particular, we welcome contributions from both the software and robotic agents communities.  One of our main goals is to bridge this divide, to create a single community of research on interactive learning agents.  To aid in communication across this interdisciplinary collection of researchers, authors are asked that in descriptions of their work they address the following questions:

1. •How explicitly pedagogical is the human teacher? At one extreme, the human is a role-model not considering the agent at all; at the other, the human is carefully formulating a curriculum.
   

2. •How much does learning depend on communication between human teacher and agent?  At one extreme, the human and agent merely observe one another interacting with the environment; at the other there is a complex dialogue between teacher and student.
   

3. •How interdependent is learned information?  At one extreme, learning can potentially happen in any order (e.g., mapping a state space); at the other, each new piece of knowledge must be formulated in terms of the previous one (e.g., Kirchoff's laws depend on current and voltage).
   

4. •What is the relative importance of how learning occurs vs. the end result of learning in the research?  At one extreme, learning from humans is just a pragmatic way of configuring a real-world system; at the other, the system is only valued for the insight it provides on human learning.
   

Submissions

We invite short and long length papers, reviews, and position papers. Submissions will be judged on technical merit, the potential to generate discussion, and their ability to foster collaboration within the community.  Additionally, authors are asked to address the bulleted questions above as appropriate.

The maximum length is 6 pages, and papers should follow AAMAS formatting guidelines. Please submit your papers to the ALIHT submission site at http://www.easychair.org/conferences/?conf=aliht2010.

Important dates

1. • Paper submission deadline:  February 2, 2010 at 11:59PM PST
   

2. • Acceptance notification: March 5, 2010
   

3. • Camera-ready deadline: March 15, 2010
   

4. • Preliminary program online: March 19, 2010
   

5. • ALIHT workshop at AAMAS: May 11, 2010