Agents teaching agents: a survey on inter-agent transfer learning

Author(s)

Da Silva, Felipe Leno ^{[1, 2]} ; Warnell, Garrett ^[3] ; Costa, Anna Helena Reali ^[1] ; Stone, Peter ^[2]

Affiliation

^[1] Univ Sao Paulo, Sao Paulo - Brazil

^[2] Univ Texas Austin, Austin, TX 78712 - USA

^[3] US Army, Res Lab, Austin, TX - USA

• Document type: Journal article
• Source: AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS; v. 34, n. 1 APR 2020.
• Web of Science Citations: 0

Abstract

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. (AU)

• FAPESP's process: 15/16310-4 - Transfer Learning in Reinforcement Learning Multi-Agent Systems
• Grantee: Felipe Leno da Silva
• Support Opportunities: Scholarships in Brazil - Doctorate
• FAPESP's process: 18/00344-5 - Reusing previous task solutions in multiagent reinforcement learning
• Grantee: Felipe Leno da Silva
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate