Low-rank Agent-specific Adaptation (lorasa) For Multi-agent Policy Learning

Abstract

Multi-agent reinforcement learning (MARL) often relies on *parameter sharing (PS)* to scale efficiently. However, purely shared policies can stifle each agent's unique specialization, reducing overall performance in heterogeneous environments. We propose \textbf\{Low-Rank Agent-Specific Adaptation (LoRASA)\}, a novel approach that treats each agent's policy as a specialized ``task'' fine-tuned from a shared backbone. Drawing inspiration from parameter-efficient transfer methods, LoRASA appends small, low-rank adaptation matrices to each layer of the shared policy, naturally inducing *parameter-space sparsity* that promotes both specialization and scalability. We evaluate LoRASA on challenging benchmarks including the StarCraft Multi-Agent Challenge (SMAC) and Multi-Agent MuJoCo (MAMuJoCo), implementing it atop widely used algorithms such as MAPPO and A2PO. Across diverse tasks, LoRASA matches or outperforms existing baselines *while reducing memory and computational overhead*. Ablation

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2025low

Related papers

• Hypermarl: Adaptive Hypernetworks For Multi-agent RL (2024)0.00
• Representation Learning For Efficient Deep Multi-agent Reinforcement Learning (2024)0.00
• Local Advantage Networks For Cooperative Multi-agent Reinforcement Learning (2021)0.00
• End-to-end Optimization Of Llm-driven Multi-agent Search Systems Via Heterogeneous-group-based Reinforcement Learning (2025)0.00
• Learning To Share In Multi-agent Reinforcement Learning (2021)0.00
• LDSA: Learning Dynamic Subtask Assignment In Cooperative Multi-agent Reinforcement Learning (2022)3.58
• A Generalized Algorithm For Multi-objective Reinforcement Learning And Policy Adaptation (2019)0.00
• MESA: Cooperative Meta-exploration In Multi-agent Learning Through Exploiting State-action Space Structure (2024)2.26