Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net
Abstract
In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control. Decentralized multi-agent reinforcement learning methods have difficulty learning decentralized policies because of the environment appearing to be non-stationary due to other agents also learning at the same time. In this paper, we address this challenge by proposing a macro-action-based decentralized multi-agent double deep recurrent Q-net (MacDec-MADDRQN) which trains each decentralized Q-net using a centralized Q-net for action selection. A generalized version of MacDec-MADDRQN with two separate training environments, called Parallel-MacDec-MADDRQN, is also presented to leverage either centralized or decentralized exploration. The advantages and the practical nature of our methods are demonstrated by achieving near-centralized results in simulation and having real robots accomplish a warehouse tool delivery task in an efficient way.
Cite
@article{arxiv.1909.08776,
title = {Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net},
author = {Yuchen Xiao and Joshua Hoffman and Tian Xia and Christopher Amato},
journal= {arXiv preprint arXiv:1909.08776},
year = {2020}
}