MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models

Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve sample efficiency. We present a novel multi-agent model-bas...

Full description

Saved in:
Bibliographic Details
Main Authors Willemsen, Daniël, Coppola, Mario, de Croon, Guido C. H. E
Format Journal Article
LanguageEnglish
Published 05.03.2021
Subjects
Computer Science - Artificial Intelligence
Computer Science - Multiagent Systems
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve sample efficiency. We present a novel multi-agent model-based RL algorithm: Multi-Agent Model-Based Policy Optimization (MAMBPO), utilizing the Centralized Learning for Decentralized Execution (CLDE) framework. CLDE algorithms allow a group of agents to act in a fully decentralized manner after training. This is a desirable property for many systems comprising of multiple robots. MAMBPO uses a learned world model to improve sample efficiency compared to model-free Multi-Agent Soft Actor-Critic (MASAC). We demonstrate this on two simulated multi-robot tasks, where MAMBPO achieves a similar performance to MASAC, but requires far fewer samples to do so. Through this, we take an important step towards making real-life learning for multi-robot systems possible.
DOI:10.48550/arxiv.2103.03662