A Roadmap Towards Improving Multi-agent Reinforcement Learning With Causal Discovery And Inference

Abstract

Causal reasoning is increasingly used in Reinforcement Learning (RL) to improve the learning process in several dimensions: efficacy of learned policies, efficiency of convergence, generalisation capabilities, safety and interpretability of behaviour. However, applications of causal reasoning to Multi-Agent RL (MARL) are still mostly unexplored. In this paper, we take the first step in investigating the opportunities and challenges of applying causal reasoning in MARL. We measure the impact of a simple form of causal augmentation in state-of-the-art MARL scenarios increasingly requiring cooperation, and with state-of-the-art MARL algorithms exploiting various degrees of collaboration between agents. Then, we discuss the positive as well as negative results achieved, giving us the chance to outline the areas where further research may help to successfully transfer causal RL to the multi-agent setting.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybriglia2025a

Related papers

• Discovering Causality For Efficient Cooperation In Multi-agent Environments (2023)0.00
• Learning By Doing: An Online Causal Reinforcement Learning Framework With Causal-aware Policy (2024)1.56
• Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms And Applications (2025)0.00
• Situation-dependent Causal Influence-based Cooperative Multi-agent Reinforcement Learning (2023)5.24
• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• Causal Influence Detection For Improving Efficiency In Reinforcement Learning (2021)0.00
• MACIE: Multi-agent Causal Intelligence Explainer For Collective Behavior Understanding (2025)2.26
• Goal Discovery With Causal Capacity For Efficient Reinforcement Learning (2025)0.00