Sequential Multi-Agent Dynamic Algorithm Configuration

TL;DR

This paper introduces Seq-MADAC, a sequential multi-agent reinforcement learning framework that considers parameter inter-dependencies in dynamic algorithm configuration, leading to improved performance over existing methods.

Contribution

The paper proposes a novel sequential advantage decomposition network within MARL to handle parameter inter-dependencies in algorithm configuration.

Findings

Seq-MADAC outperforms state-of-the-art MARL methods.

Demonstrates strong generalization across problem classes.

Effective in configuring complex algorithms with inter-dependent parameters.

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.