While recent work in reinforcement learning (RL) has led to agents capable of solving increasingly complex tasks, the issue of high sample complexity is still a major concern. This issue has motivated the development of additional techniques that augment RL methods in an attempt to increase task learning speed. In particular, inter-agent teaching -- endowing agents with the ability to respond to instructions from others -- has been responsible for many of these developments. RL agents that can leverage instruction from a more competent teacher have been shown to be able to learn tasks significantly faster than agents that cannot take advantage of such instruction. That said, the inter-agent teaching paradigm presents many new challenges due to, among other factors, differences between the agents involved in the teaching interaction. As a result, many inter-agent teaching methods work only in restricted settings and have proven difficult to generalize to new domains or scenarios. In this article, we propose two frameworks that provide a comprehensive view of the challenges associated with inter-agent teaching.We highlight state-of-the-art solutions, open problems, prospective applications, and argue that new research in this area should be developed in the context of the proposed frameworks.

PDF

Autonomous Agents and Multi-Agent Systems (2020).

@article{JAAMAS20-Leno, title={Agents teaching agents: a survey on inter-agent transfer learning}, author={Felipe Leno Da Silva and Garrett Warnell and Anna Helena Reali Costa and Peter Stone}, journal={Autonomous Agents and Multi-Agent Systems}, month={January}, url="http://www.cs.utexas.edu/users/ai-lab?JAAMAS20-Leno", year={2020} }