Settling Decentralized Multi-agent Coordinated Exploration By Novelty Sharing

Abstract

Exploration in decentralized cooperative multi-agent reinforcement learning faces two challenges. One is that the novelty of global states is unavailable, while the novelty of local observations is biased. The other is how agents can explore in a coordinated way. To address these challenges, we propose MACE, a simple yet effective multi-agent coordinated exploration method. By communicating only local novelty, agents can take into account other agents' local novelty to approximate the global novelty. Further, we newly introduce weighted mutual information to measure the influence of one agent's action on other agents' accumulated novelty. We convert it as an intrinsic reward in hindsight to encourage agents to exert more influence on other agents' exploration and boost coordinated exploration. Empirically, we show that MACE achieves superior performance in three multi-agent environments with sparse rewards.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyjiang2024settling

Related papers

• Wonder Wins Ways: Curiosity-driven Exploration Through Multi-agent Contextual Calibration (2025)0.00
• MESA: Cooperative Meta-exploration In Multi-agent Learning Through Exploiting State-action Space Structure (2024)2.26
• Episodic Multi-agent Reinforcement Learning With Curiosity-driven Exploration (2021)0.00
• Coordinated Exploration Via Intrinsic Rewards For Multi-agent Reinforcement Learning (2019)0.00
• Curiosity-driven Multi-agent Exploration With Mixed Objectives (2022)0.00
• Prioritized Guidance For Efficient Multi-agent Reinforcement Learning Exploration (2019)0.00
• Novelty-guided Data Reuse For Efficient And Diversified Multi-agent Reinforcement Learning (2024)2.26
• Individual Contributions As Intrinsic Exploration Scaffolds For Multi-agent Reinforcement Learning (2024)2.80