English

Separation of Concerns in Reinforcement Learning

Machine Learning 2017-03-30 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.1612.05159,
  title  = {Separation of Concerns in Reinforcement Learning},
  author = {Harm van Seijen and Mehdi Fatemi and Joshua Romoff and Romain Laroche},
  journal= {arXiv preprint arXiv:1612.05159},
  year   = {2017}
}
R2 v1 2026-06-22T17:25:03.142Z