# Sequential Multi-Agent Dynamic Algorithm Configuration

arXiv: https://arxiv.org/abs/2510.23535 · HTML: https://mlsanity.com/paper/2510.23535/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [Multiagent Cooperation and Competition with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.08779/) (2015)
- [Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions](https://mlsanity.com/paper/2309.10150/) (2023)
- [ParamILS: An Automatic Algorithm Configuration Framework](https://mlsanity.com/paper/1401.3492/) (2014)
- [Discrete Sequential Prediction of Continuous Actions for Deep RL](https://mlsanity.com/paper/1705.05035/) (2017)
- [Automated Dynamic Algorithm Configuration](https://mlsanity.com/paper/2205.13881/) (2022)
- [A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment](https://mlsanity.com/paper/2312.01058/) (2023)
- [Multi-agent Dynamic Algorithm Configuration](https://mlsanity.com/paper/2210.06835/) (2022)
- [Multi-agent Embodied AI: Advances and Future Directions](https://mlsanity.com/paper/2505.05108/) (2025)
- [Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2206.07505/) (2022)
- [DACBench: A Benchmark Library for Dynamic Algorithm Configuration](https://mlsanity.com/paper/2105.08541/) (2021)
- [Learning adaptive differential evolution algorithm from optimization experiences by policy gradient](https://mlsanity.com/paper/2102.03572/) (2021)
- [Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization](https://mlsanity.com/paper/2411.00625/) (2024)
- [Learning Heuristic Selection with Dynamic Algorithm Configuration](https://mlsanity.com/paper/2006.08246/) (2020)
- [Maximum Entropy Heterogeneous-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.10715/) (2023)
- [ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency](https://mlsanity.com/paper/2211.16068/) (2022)
- [ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning](https://mlsanity.com/paper/2412.07507/) (2024)
- [Online Selection of CMA-ES Variants](https://mlsanity.com/paper/1904.07801/) (2019)
- [A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective](https://mlsanity.com/paper/2403.07262/) (2024)
- [Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization](https://mlsanity.com/paper/2408.10672/) (2024)
- [Meta-Black-Box-Optimization through Offline Q-function Learning](https://mlsanity.com/paper/2505.02010/) (2025)
- [Decomposition Multi-Objective Evolutionary Optimization: From State-of-the-Art to Future Opportunities](https://mlsanity.com/paper/2108.09588/) (2021)
- [CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC](https://mlsanity.com/paper/2407.05789/) (2024)

## Built on by (most cited first, 3 of 3)

- [COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams](https://mlsanity.com/paper/2604.17693/) (2026)
- [Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning](https://mlsanity.com/paper/2606.10129/) (2026)
- [Rethinking Learnability in Offline Data-driven Optimization](https://mlsanity.com/paper/2609.01493/) (2026)

## Abstract (arXiv)

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.