{"ID":2849754,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23535","arxiv_id":"2510.23535","title":"Sequential Multi-Agent Dynamic Algorithm Configuration","abstract":"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.","short_abstract":"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 con...","url_abs":"https://arxiv.org/abs/2510.23535","url_pdf":"https://arxiv.org/pdf/2510.23535v1","authors":"[\"Chen Lu\",\"Ke Xue\",\"Lei Yuan\",\"Yao Wang\",\"Yaoyuan Wang\",\"Sheng Fu\",\"Chao Qian\"]","published":"2025-10-27T17:11:03Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.NE\"]","methods":"[\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":607738,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2849754,"paper_url":"https://arxiv.org/abs/2510.23535","paper_title":"Sequential Multi-Agent Dynamic Algorithm Configuration","repo_url":"https://github.com/lamda-bbo/seq-madac","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}