Spectra: Scalable Multi-agent Reinforcement Learning With Permutation-free Networks

Abstract

In cooperative multi-agent reinforcement learning (MARL), the permutation problem where the state space grows exponentially with the number of agents reduces sample efficiency. Additionally, many existing architectures struggle with scalability, relying on a fixed structure tied to a specific number of agents, limiting their applicability to environments with a variable number of entities. While approaches such as graph neural networks (GNNs) and self-attention mechanisms have progressed in addressing these challenges, they have significant limitations as dense GNNs and self-attention mechanisms incur high computational costs. To overcome these limitations, we propose a novel agent network and a non-linear mixing network that ensure permutation-equivariance and scalability, allowing them to generalize to environments with various numbers of agents. Our agent network significantly reduces computational complexity, and our scalable hypernetwork enables efficient weight generation for non

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypark2025spectra

Related papers

• Multi-agent Reinforcement Learning In Stochastic Networked Systems (2020)0.00
• Permutation Invariant Policy Optimization For Mean-field Multi-agent Reinforcement Learning: A Principled Approach (2021)0.00
• PIC: Permutation Invariant Critic For Multi-agent Deep Reinforcement Learning (2019)0.00
• Scalable Multi-agent Reinforcement Learning For Networked Systems With Average Reward (2020)0.00
• Enhancing Heterogeneous Multi-agent Cooperation In Decentralized MARL Via Gnn-driven Intrinsic Rewards (2024)0.00
• Hypermarl: Adaptive Hypernetworks For Multi-agent RL (2024)0.00
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34
• Fully Decentralized Multi-agent Reinforcement Learning With Networked Agents (2018)0.00