Adaptive parameter sharing for multi-agent reinforcement learning

2023-12-14 · Dapeng Li, Na Lou, Bin Zhang, Zhiwei Xu, Guoliang Fan

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.

📄 PDF Abstract BibTeX arXiv:2312.09009

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMulti-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Multi-Agent Reinforcement Learning for Dynamic Mobility Resource Allocation with Hierarchical Adaptive Grouping

2025-07-27 · Farshid Nooshi, Suining He arxiv

Allocating mobility resources (e.g., shared bikes/e-scooters, ride-sharing vehicles) is crucial for rebalancing the mobility demand and supply in the urban environments. We propose in this work a novel multi-agent reinfo…

Multi-agent Reinforcement Learning

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

2024-10-11 · Xinran Li, Ling Pan, Jun Zhang

In multi-agent reinforcement learning (MARL), parameter sharing is commonly employed to enhance sample efficiency. However, the popular approach of full parameter sharing often leads to homogeneous policies among agents,…

Diversity MuJoCo Multi-agent Reinforcement Learning reinforcement-learning+2

Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing

2020-02-12 · Ge Liu, Rui Wu, Heng-Tze Cheng, Jing Wang 외

Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recomme…

Atari Games Decision Making Deep Reinforcement Learning Recommendation Systems+3

Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing

2021-02-15 · Filippos Christianos, Georgios Papoudakis, Arrasy Rahman, Stefano V. Albrecht

Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number …

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

2024-12-05 · Kale-ab Abebe Tessera, Arrasy Rahman, Amos Storkey, Stefano V. Albrecht

Adaptability to specialised or homogeneous behaviours is critical in cooperative multi-agent reinforcement learning (MARL). Parameter sharing (PS) techniques, common for efficient adaptation, often limit behavioural dive…

Diversity Multi-agent Reinforcement Learning