Separation of Concerns in Reinforcement Learning

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.

References in corpus (5)

• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• Learning and Transfer of Modulated Locomotor Controllers
• Learning values across many orders of magnitude
• Learning Purposeful Behaviour in the Absence of Rewards

Cited by in corpus (2)

• Multi-Advisor Reinforcement Learning
• On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning