# Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning

arXiv: https://arxiv.org/abs/2502.05573 · HTML: https://mlsanity.com/paper/2502.05573/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Builds on (most cited first, 28 of 28)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (2017)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation](https://mlsanity.com/paper/2210.07558/) (2022)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/1703.06182/) (2017)
- [Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.07169/) (2020)
- [Celebrating Diversity in Shared Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.02195/) (2021)
- [Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing](https://mlsanity.com/paper/2102.07475/) (2021)
- [An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2409.03052/) (2024)
- [Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2303.00912/) (2023)
- [Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1710.00336/) (2017)
- [Policy Distillation and Value Matching in Multiagent Reinforcement Learning](https://mlsanity.com/paper/1903.06592/) (2019)
- [Adaptive parameter sharing for multi-agent reinforcement learning](https://mlsanity.com/paper/2312.09009/) (2023)
- [Identifying Policy Gradient Subspaces](https://mlsanity.com/paper/2401.06604/) (2024)
- [Real-time Policy Distillation in Deep Reinforcement Learning](https://mlsanity.com/paper/1912.12630/) (2019)
- [Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2311.00865/) (2023)
- [Multi-Task Multi-Agent Shared Layers are Universal Cognition of Multi-Agent Coordination](https://mlsanity.com/paper/2312.15674/) (2023)
- [Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2408.13567/) (2024)
- [Discovering Behavioral Modes in Deep Reinforcement Learning Policies Using Trajectory Clustering in Latent Space](https://mlsanity.com/paper/2402.12939/) (2024)

## Built on by (most cited first, 4 of 4)

- [Onboard Optimization and Learning: A Survey](https://mlsanity.com/paper/2505.08793/) (2025)
- [LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.09756/) (2025)
- [Feedback Attribution and Representation Geometry: Metrics for Comparing Individual and Shared Rewards in MARL](https://mlsanity.com/paper/2607.16524/) (2026)
- [Training Small LLMs as Spatial Multi-Agent Policies](https://mlsanity.com/paper/2608.01425/) (2026)

## Abstract (arXiv)

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 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 studies on adapter rank, placement, and timing validate the method's flexibility and efficiency. Our results suggest LoRASA's potential to establish a new norm for MARL policy parameterization: combining a shared foundation for coordination with low-rank agent-specific refinements for individual specialization.