Autonomously Reusing Knowledge in Multiagent Reinforcement Learning

Autonomously Reusing Knowledge in Multiagent Reinforcement Learning

Felipe Leno Da Silva, Matthew E. Taylor, Anna Helena Reali Costa

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Survey track. Pages 5487-5493. https://doi.org/10.24963/ijcai.2018/774

Autonomous agents are increasingly required to solve complex tasks; hard-coding behaviors has become infeasible. Hence, agents must learn how to solve tasks via interactions with the environment. In many cases, knowledge reuse will be a core technology to keep training times reasonable, and for that, agents must be able to autonomously and consistently reuse knowledge from multiple sources, including both their own previous internal knowledge and from other agents. In this paper, we provide a literature review of methods for knowledge reuse in Multiagent Reinforcement Learning. We define an important challenge problem for the AI community, survey the existent methods, and discuss how they can all contribute to this challenging problem. Moreover, we highlight gaps in the current literature, motivating "low-hanging fruit'' for those interested in the area. Our ambition is that this paper will encourage the community to work on this difficult and relevant research challenge.
Keywords:
Agent-based and Multi-agent Systems: Multi-agent Learning
Machine Learning: Reinforcement Learning
Machine Learning: Transfer, Adaptation, Multi-task Learning