Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.23535 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908614990495744 |
|---|---|
| author | Lu, Chen Xue, Ke Yuan, Lei Wang, Yao Wang, Yaoyuan Fu, Sheng Qian, Chao |
| author_facet | Lu, Chen Xue, Ke Yuan, Lei Wang, Yao Wang, Yaoyuan Fu, Sheng Qian, Chao |
| contents | Dynamic algorithm configuration (DAC) is a recent trend in automated machine learning, which can dynamically adjust the algorithm's configuration during the execution process and relieve users from tedious trial-and-error tuning tasks. Recently, multi-agent reinforcement learning (MARL) approaches have improved the configuration of multiple heterogeneous hyperparameters, making various parameter configurations for complex algorithms possible. However, many complex algorithms have inherent inter-dependencies among multiple parameters (e.g., determining the operator type first and then the operator's parameter), which are, however, not considered in previous approaches, thus leading to sub-optimal results. In this paper, we propose the sequential multi-agent DAC (Seq-MADAC) framework to address this issue by considering the inherent inter-dependencies of multiple parameters. Specifically, we propose a sequential advantage decomposition network, which can leverage action-order information through sequential advantage decomposition. Experiments from synthetic functions to the configuration of multi-objective optimization algorithms demonstrate Seq-MADAC's superior performance over state-of-the-art MARL methods and show strong generalization across problem classes. Seq-MADAC establishes a new paradigm for the widespread dependency-aware automated algorithm configuration. Our code is available at https://github.com/lamda-bbo/seq-madac. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23535 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sequential Multi-Agent Dynamic Algorithm Configuration Lu, Chen Xue, Ke Yuan, Lei Wang, Yao Wang, Yaoyuan Fu, Sheng Qian, Chao Machine Learning Neural and Evolutionary Computing Dynamic algorithm configuration (DAC) is a recent trend in automated machine learning, which can dynamically adjust the algorithm's configuration during the execution process and relieve users from tedious trial-and-error tuning tasks. Recently, multi-agent reinforcement learning (MARL) approaches have improved the configuration of multiple heterogeneous hyperparameters, making various parameter configurations for complex algorithms possible. However, many complex algorithms have inherent inter-dependencies among multiple parameters (e.g., determining the operator type first and then the operator's parameter), which are, however, not considered in previous approaches, thus leading to sub-optimal results. In this paper, we propose the sequential multi-agent DAC (Seq-MADAC) framework to address this issue by considering the inherent inter-dependencies of multiple parameters. Specifically, we propose a sequential advantage decomposition network, which can leverage action-order information through sequential advantage decomposition. Experiments from synthetic functions to the configuration of multi-objective optimization algorithms demonstrate Seq-MADAC's superior performance over state-of-the-art MARL methods and show strong generalization across problem classes. Seq-MADAC establishes a new paradigm for the widespread dependency-aware automated algorithm configuration. Our code is available at https://github.com/lamda-bbo/seq-madac. |
| title | Sequential Multi-Agent Dynamic Algorithm Configuration |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2510.23535 |