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.
@article{arxiv.2103.03662,
title = {MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models},
author = {Daniël Willemsen and Mario Coppola and Guido C. H. E. de Croon},
journal= {arXiv preprint arXiv:2103.03662},
year = {2021}
}
Comments
Submitted to 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)