Separation of Concerns in Reinforcement Learning

2016/12/15 by van Seijen, Harm, Fatemi, Mehdi, Romoff, Joshua +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1612.05159

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.

Related

• Efficient Training in Multi-Agent Reinforcement Learning: A Communication-Free Framework for the Box-Pushing Problem
• Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents
• Policy Distillation and Value Matching in Multiagent Reinforcement Learning
• Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition
• Learning Symbolic Task Decompositions for Multi-Agent Teams