# Adaptive parameter sharing for multi-agent reinforcement learning

arXiv: https://arxiv.org/abs/2312.09009 · HTML: https://mlsanity.com/paper/2312.09009/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control](https://mlsanity.com/paper/1903.04527/) (2019)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing](https://mlsanity.com/paper/2102.07475/) (2021)
- [A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systems](https://mlsanity.com/paper/1506.01170/) (2015)
- [Recent Advances on Neural Network Pruning at Initialization](https://mlsanity.com/paper/2103.06460/) (2021)
- [Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN](https://mlsanity.com/paper/2308.08333/) (2023)
- [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)
- [From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL](https://mlsanity.com/paper/2304.14656/) (2023)
- [Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2204.09418/) (2022)
- [Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.10351/) (2023)
- [Style Miner: Find Significant and Stable Explanatory Factors in Time Series with Constrained Reinforcement Learning](https://mlsanity.com/paper/2303.11716/) (2023)
- [SEA: A Spatially Explicit Architecture for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.12532/) (2023)

## Built on by (most cited first, 6 of 6)

- [HyperMARL: Adaptive Hypernetworks for Multi-Agent RL](https://mlsanity.com/paper/2412.04233/) (2024)
- [Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2404.17780/) (2024)
- [Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning](https://mlsanity.com/paper/2502.05573/) (2025)
- [Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.06476/) (2026)
- [Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.12388/) (2026)
- [LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.09756/) (2025)

## Abstract (arXiv)

Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems. However, the effectiveness of parameter sharing largely depends on the environment setting. When agents have different identities or tasks, naive parameter sharing makes it difficult to generate sufficiently differentiated strategies for agents. Inspired by research pertaining to the brain in biology, we propose a novel parameter sharing method. It maps each type of agent to different regions within a shared network based on their identity, resulting in distinct subnetworks. Therefore, our method can increase the diversity of strategies among different agents without introducing additional training parameters. Through experiments conducted in multiple environments, our method has shown better performance than other parameter sharing methods.