Separation of Concerns in Reinforcement Learning
This approach addresses efficiency and specialization in reinforcement learning, though it appears incremental as it builds on hierarchical decomposition methods.
The paper tackles the problem of single-agent tasks by using multiple specialized agents, resulting in a framework that enables training on different task aspects and facilitates knowledge transfer through agent sharing.
In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantages: 1) it allows for training specialized agents on different parts of the task, and 2) it provides a new way to transfer knowledge, by transferring trained agents. Our framework generalizes the traditional hierarchical decomposition, in which, at any moment in time, a single agent has control until it has solved its particular subtask. We illustrate our framework with empirical experiments on two domains.