MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{willemsen2021mambpo,
author = {Daniël Willemsen and Mario Coppola and Guido C. H. E. de Croon},
title = {{MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models}},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
year = {2021},
doi = {10.1109/iros51168.2021.9635836},
}Loading related content...