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
Published in:Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 5635 - 5640
Main Authors: Willemsen, Daniel, Coppola, Mario, de Croon, Guido C.H.E.
Format: Conference Proceeding
Language:English
Published: IEEE 27.09.2021
Subjects:
Intelligent robots
Multi-robot systems
Optimization
Reinforcement learning
Task analysis
Training
ISSN:2153-0866
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
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.
ISSN:2153-0866
DOI:10.1109/IROS51168.2021.9635836