MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Qi, Guo, Jingxiang, Lin, Sixu, Ma, Shuaikang, Zhu, Jinxuan, Li, Yanjie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914976637124608
author Liu, Qi
Guo, Jingxiang
Lin, Sixu
Ma, Shuaikang
Zhu, Jinxuan
Li, Yanjie
author_facet Liu, Qi
Guo, Jingxiang
Lin, Sixu
Ma, Shuaikang
Zhu, Jinxuan
Li, Yanjie
contents This paper proposes a novel method to improve locomotion learning for a single quadruped robot using multi-agent deep reinforcement learning (MARL). Many existing methods use single-agent reinforcement learning for an individual robot or MARL for the cooperative task in multi-robot systems. Unlike existing methods, this paper proposes using MARL for the locomotion learning of a single quadruped robot. We develop a learning structure called Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion (MASQ), considering each leg as an agent to explore the action space of the quadruped robot, sharing a global critic, and learning collaboratively. Experimental results indicate that MASQ not only speeds up learning convergence but also enhances robustness in real-world settings, suggesting that applying MASQ to single robots such as quadrupeds could surpass traditional single-robot reinforcement learning approaches. Our study provides insightful guidance on integrating MARL with single-robot locomotion learning.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion
Liu, Qi
Guo, Jingxiang
Lin, Sixu
Ma, Shuaikang
Zhu, Jinxuan
Li, Yanjie
Robotics
This paper proposes a novel method to improve locomotion learning for a single quadruped robot using multi-agent deep reinforcement learning (MARL). Many existing methods use single-agent reinforcement learning for an individual robot or MARL for the cooperative task in multi-robot systems. Unlike existing methods, this paper proposes using MARL for the locomotion learning of a single quadruped robot. We develop a learning structure called Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion (MASQ), considering each leg as an agent to explore the action space of the quadruped robot, sharing a global critic, and learning collaboratively. Experimental results indicate that MASQ not only speeds up learning convergence but also enhances robustness in real-world settings, suggesting that applying MASQ to single robots such as quadrupeds could surpass traditional single-robot reinforcement learning approaches. Our study provides insightful guidance on integrating MARL with single-robot locomotion learning.
title MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion
topic Robotics
url https://arxiv.org/abs/2408.13759