Haoyu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haoyu Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Cong Yu
Tsinghua University, Shenzhen, China
1 shared publication - Junbo Tan
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
1 shared publication - Tiantian Zhang
Tsinghua University
1 shared publication - Xinyang Li
Tsinghua University, Shenzhen, China
1 shared publication - Xueqian Wang
Tsinghua University
1 shared publication - Yongzhe Chang
Tsinghua University, Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 10 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 392-401
Surrogate-Assisted Evolutionary Multi-Agent Reinforcement Learning with Adaptive Fitness Evaluation
Deep Multi-Agent Reinforcement Learning (MARL) excels in co-operative tasks but often struggles with local optima in high - dimensional joint action spaces. In contrast, Evolutionary Algorithms (EAs) offer robust global exploration capabilities. Although hybrid approaches seek to combine the strengths of both paradigms, they typically face a critical bottleneck: the prohibitive sample cost of evaluating large populations via environment rollouts. To address this challenge, we propose Surrogate-assisted Evolutionary Multi-Agent Reinforcement Learning (SEMARL), a unified framework that synergizes gradient-based refinement with surrogate-assisted evolutionary search. SEMARL employs a cooperative co-evolutionary architecture to maintain diverse agent policies and injects gradient-refined parameters into the population to accelerate convergence. Crucially, we leverage the centralized critic from the gradient learner as a computationally efficient surrogate for fitness estimation. To prevent misleading guidance from an inaccurate critic, we introduce an adaptive reliability control mechanism based on temporal difference (TD) error, which dynamically regulates the surrogate's influence. Experiments on the Multi-Agent MuJoCo benchmark demonstrate that SEMARL significantly outperforms other algorithms, achieving superior asymptotic performance with substantially higher sample efficiency.
- 10 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 392-401
Open AccessSurrogate-Assisted Evolutionary Multi-Agent Reinforcement Learning with Adaptive Fitness Evaluation
Deep Multi-Agent Reinforcement Learning (MARL) excels in co-operative tasks but often struggles with local optima in high - dimensional joint action spaces. In contrast, Evolutionary Algorithms (EAs) offer robust global exploration capabilities. Although hybrid approaches seek to combine the strengths of both paradigms, they typically face a critical bottleneck: the prohibitive sample cost of evaluating large populations via environment rollouts. To address this challenge, we propose Surrogate-assisted Evolutionary Multi-Agent Reinforcement Learning (SEMARL), a unified framework that synergizes gradient-based refinement with surrogate-assisted evolutionary search. SEMARL employs a cooperative co-evolutionary architecture to maintain diverse agent policies and injects gradient-refined parameters into the population to accelerate convergence. Crucially, we leverage the centralized critic from the gradient learner as a computationally efficient surrogate for fitness estimation. To prevent misleading guidance from an inaccurate critic, we introduce an adaptive reliability control mechanism based on temporal difference (TD) error, which dynamically regulates the surrogate's influence. Experiments on the Multi-Agent MuJoCo benchmark demonstrate that SEMARL significantly outperforms other algorithms, achieving superior asymptotic performance with substantially higher sample efficiency.