English

The challenge of redundancy on multi-agent value factorisation

Artificial Intelligence 2023-04-04 v1

Abstract

In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution where a central critic conditions the policies of the cooperative agents based on a central state. It has been shown, that in cases with large numbers of redundant agents these methods become less effective. In a more general case, there is likely to be a larger number of agents in an environment than is required to solve the task. These redundant agents reduce performance by enlarging the dimensionality of both the state space and and increasing the size of the joint policy used to solve the environment. We propose leveraging layerwise relevance propagation (LRP) to instead separate the learning of the joint value function and generation of local reward signals and create a new MARL algorithm: relevance decomposition network (RDN). We find that although the performance of both baselines VDN and Qmix degrades with the number of redundant agents, RDN is unaffected.

Keywords

Cite

@article{arxiv.2304.00009,
  title  = {The challenge of redundancy on multi-agent value factorisation},
  author = {Siddarth Singh and Benjamin Rosman},
  journal= {arXiv preprint arXiv:2304.00009},
  year   = {2023}
}

Comments

Published at the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023). 2 Pages, 1 Figure

R2 v1 2026-06-28T09:43:44.875Z