From Consistency to Collaborative Discovery: MFEA-CoD for Multitask Novelty Search

2026-07-01

AI Summary

This work addresses the limitations of traditional multitask evolutionary algorithms, which rely on inter-task consistency and struggle to discover diverse, novel behaviors when explicit objectives are absent or deceptive. To overcome this, the authors propose MFEA-CoD, a novel algorithm that shifts the multitask evolutionary paradigm from consistency exploitation to collaborative discovery. Operating within a unified search space, MFEA-CoD coordinates multiple novelty search tasks, employs a multitask repulsion operator to avoid redundant exploration, and incorporates an adaptive cross-task transfer mechanism that dynamically leverages shared regions of high novelty. This approach establishes the first unified framework integrating multitask novelty search with novelty-augmented optimization, significantly improving the efficiency of discovering diverse and novel solutions across benchmark domains—including synthetic basins, maze navigation, MuJoCo policy optimization, and generative tasks—with particularly strong performance in deceptive environments.

Abstract

Evolutionary multitasking (EMT) has shown strong capability in solving multiple optimization problems simultaneously by exploiting latent inter-task consistency, such as similarities in promising solutions or search directions. However, most existing EMT studies remain focused on objective-driven optimization, where such consistency is mainly used to accelerate convergence toward predefined optima. In this paper, we move EMT from consistency to collaborative discovery and propose a multifactorial evolutionary algorithm with collaborative discovery (MFEA-CoD) for multitask novelty search. Unlike conventional EMT, MFEA-CoD coordinates multiple novelty search tasks to collaboratively discover behaviorally novel solutions rather than merely transferring consistent search information for faster convergence. Specifically, a multitask repulsion operator encourages different tasks to explore distinct regions of the unified search space, thereby reducing redundant behavioral discoveries. Meanwhile, an adaptive inter-task transfer mechanism exploits shared discovery opportunities in overlapping novelty-improving regions by adjusting the transfer probability according to the online contribution of transferred information. Furthermore, MFEA-CoD is extended to multitask novelty-augmented optimization, where behavioral novelty is jointly considered with objective information to alleviate premature convergence caused by deceptive objectives. Experiments on synthetic basin-type problems, deceptive maze navigation problems, MuJoCo policy optimization problems, and generative novelty search problems demonstrate that MFEA-CoD improves the efficiency of discovering diverse novel solutions and shows clear advantages in deceptive objective landscapes.

Problem

• evolutionary multitasking
• novelty search
• collaborative discovery
• deceptive objectives
• behavioral diversity

Innovation

• multitask novelty search
• collaborative discovery
• evolutionary multitasking
• adaptive transfer
• behavioral diversity