Learning Independently from Causality in Multi-Agent Environments
Preprint
Abstract
Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in MARL that denotes the event when some of the agents in a MARL team do not contribute to the common goal, letting the teammates do all the work. In this work, we aim to investigate this problem from a causality-based perspective. We intend to create the bridge between the fields of MARL and causality and argue about the usefulness of this link. We study a fully decentralised MARL setup where agents need to learn cooperation strategies and show that there is a causal relation between individual observations and the team reward. The experiments carried show how this relation can be used to improve independent agents in MARL, resulting not only on better performances as a team but also on the rise of more intelligent behaviours on individual agents.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Multi-Agent Reinforcement Learning: A Review of Challenges and ApplicationsApplied Sciences, 2021
- Review of Causal Discovery Methods Based on Graphical ModelsFrontiers in Genetics, 2019
- Multiagent cooperation and competition with deep reinforcement learningPLOS ONE, 2017
- Spurious causalities with transfer entropyPhysical Review E, 2013
- Granger Causality and Transfer Entropy Are Equivalent for Gaussian VariablesPhysical Review Letters, 2009
- Causality detection based on information-theoretic approaches in time series analysisPhysics Reports, 2007
- Measuring Information TransferPhysical Review Letters, 2000
- Investigating Causal Relations by Econometric Models and Cross-spectral MethodsEconometrica, 1969