Situation-dependent Causal Influence-based Cooperative Multi-agent Reinforcement Learning
2023 · Xiao Du, Yutong Ye, Pengyu Zhang, et al.
Abstract
Learning to collaborate has witnessed significant progress in multi-agent reinforcement learning (MARL). However, promoting coordination among agents and enhancing exploration capabilities remain challenges. In multi-agent environments, interactions between agents are limited in specific situations. Effective collaboration between agents thus requires a nuanced understanding of when and how agents' actions influence others. To this end, in this paper, we propose a novel MARL algorithm named Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning (SCIC), which incorporates a novel Intrinsic reward mechanism based on a new cooperation criterion measured by situation-dependent causal influence among agents. Our approach aims to detect inter-agent causal influences in specific situations based on the criterion using causal intervention and conditional mutual information. This effectively assists agents in exploring states that can positively impact other a
Authors
(none)
Tags
Stats
Related papers
- Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
- Influence-based Reinforcement Learning For Intrinsically-motivated Agents (2021)0.00
- Discovering Causality For Efficient Cooperation In Multi-agent Environments (2023)0.00
- PMIC: Improving Multi-agent Reinforcement Learning With Progressive Mutual Information Collaboration (2022)0.00
- A Roadmap Towards Improving Multi-agent Reinforcement Learning With Causal Discovery And Inference (2025)0.00
- Cautiously-optimistic Knowledge Sharing For Cooperative Multi-agent Reinforcement Learning (2023)5.84
- Contextual Knowledge Sharing In Multi-agent Reinforcement Learning With Decentralized Communication And Coordination (2025)0.00
- Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00