发表机构
College of Computing & Data Science, Nanyang Technological University; School of Computer Science, China University of Geosciences; School of Intelligent Rail Transportation, Dalian Jiaotong University; School of Mechanical Sciences, Indian Institute of Technology, Goa（南洋理工大学计算与数据科学学院; 中国地质大学计算机学院; 大连交通大学智能轨道交通学院; 印度理工学院果阿分校机械科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MFEA-CoD算法，将进化多任务从一致性迁移转向协同发现，通过多任务排斥和自适应迁移机制，在多任务新颖性搜索中高效发现行为新颖解，并扩展至新颖性增强优化以应对欺骗性目标。
AI 中文摘要
进化多任务（EMT）通过利用潜在的任务间一致性（如相似的有希望解或搜索方向）在同时解决多个优化问题方面展现出强大能力。然而，现有EMT研究大多仍聚焦于目标驱动优化，其中这种一致性主要用于加速向预定义最优解的收敛。本文中，我们将EMT从一致性转向协同发现，并提出一种带协同发现的多因子进化算法（MFEA-CoD）用于多任务新颖性搜索。与传统EMT不同，MFEA-CoD协调多个新颖性搜索任务以协同发现行为新颖的解，而非仅仅迁移一致的搜索信息以加快收敛。具体而言，多任务排斥算子鼓励不同任务探索统一搜索空间中的不同区域，从而减少冗余的行为发现。同时，自适应任务间迁移机制通过根据迁移信息的在线贡献调整迁移概率，利用重叠的新颖性改进区域中的共享发现机会。此外，MFEA-CoD被扩展至多任务新颖性增强优化，其中行为新颖性与目标信息共同考虑，以缓解由欺骗性目标导致的早熟收敛。在合成盆地型问题、欺骗性迷宫导航问题、MuJoCo策略优化问题和生成式新颖性搜索问题上的实验表明，MFEA-CoD提高了发现多样新颖解的效率，并在欺骗性目标景观中展现出明显优势。
英文摘要
Novelty Search (NS) promotes exploration by rewarding behaviorally novel solutions rather than directly optimizing predefined objectives, making it particularly useful when objective guidance is sparse or deceptive. However, existing NS methods are typically designed for a single search task. When multiple related NS tasks are considered independently, their search processes may repeatedly explore similar regions or rediscover solutions that could be useful across tasks, leading to redundant use of the evaluation budget. To address this issue, we formulate a multitask novelty search setting and propose Multitask Novelty Search with Cross-Task Collaborative Discovery (MTNS-CoD). The central idea is to coordinate discovery across tasks so that different task-specific searches explore complementary regions while useful discoveries can still be reused across tasks. Specifically, MTNS-CoD introduces a multitask repulsion mechanism to discourage redundant exploration in similar genotype regions, together with an adaptive inter-task transfer mechanism that adjusts transfer probabilities according to the observed utility of cross-task exchanges during evolution. Their joint use promotes complementary exploration while selectively reusing beneficial discoveries. We further extend MTNS-CoD to novelty-augmented optimization, where behavioral novelty and objective information are jointly considered to support exploration under deceptive objective landscapes. Experiments on synthetic benchmarks, deceptive maze navigation, MuJoCo policy optimization, and generative novelty search show that MTNS-CoD can improve behavioral discovery and search coverage over the considered single-task and multitask baselines, with additional benefits observed on problems containing deceptive objectives.
