Integrating Agent Advice and Previous Task Solutions in Multiagent Reinforcement Learning

Reinforcement learning methods have successfully been applied to build autonomous agents that solve challenging sequential decisionmaking problems. However, agents need a long time to learn a task, especially when multiple autonomous agents are in the environment. This research aims to propose a Transfer Learning framework to accelerate learning by combining two knowledge sources: (i) previously learned tasks; and (ii) advice from a more experienced agent. The definition of such framework requires answering several challenging research questions, including: How to abstract and represent knowledge, in order to allow generalization and posterior reuse?, How and when to transfer and receive knowledge in an efficient manner?, and How to consistently combine knowledge from several sources?