RLEMMO: Evolutionary Multimodal Optimization Assisted By Deep Reinforcement Learning
It addresses the challenge of finding all optimal solutions in multimodal optimization for researchers and practitioners, but it is incremental as it builds on existing evolutionary methods with reinforcement learning enhancements.
The paper tackles multimodal optimization problems by proposing RLEMMO, a framework that uses deep reinforcement learning to adjust individual-level search strategies, achieving competitive performance on the CEC2013 benchmark.
Solving multimodal optimization problems (MMOP) requires finding all optimal solutions, which is challenging in limited function evaluations. Although existing works strike the balance of exploration and exploitation through hand-crafted adaptive strategies, they require certain expert knowledge, hence inflexible to deal with MMOP with different properties. In this paper, we propose RLEMMO, a Meta-Black-Box Optimization framework, which maintains a population of solutions and incorporates a reinforcement learning agent for flexibly adjusting individual-level searching strategies to match the up-to-date optimization status, hence boosting the search performance on MMOP. Concretely, we encode landscape properties and evolution path information into each individual and then leverage attention networks to advance population information sharing. With a novel reward mechanism that encourages both quality and diversity, RLEMMO can be effectively trained using a policy gradient algorithm. The experimental results on the CEC2013 MMOP benchmark underscore the competitive optimization performance of RLEMMO against several strong baselines.