The mutation operations and related control parameters play important roles in the performance of the differential evolution algorithm. Learning optimal policies for these strategies and parameters through reinforcement learning is a hot topic. However, most of the current studies focus on either mutation strategy selection or the control parameters alone while the others keep fixed or self-adaptive, resulting in deteriorated performances. To address this gap, this paper proposes a framework for the joint adaptation of mutation strategies and related control parameters based on deep reinforcement learning. In this method, the distributed proximal policy optimization algorithm is employed to train the agents to dynamically select the optimal combination of mutation strategies and control parameters. To enhance the agent’s learning of the optimal policy, information derived from fitness landscape analysis is incorporated into the state representations. The training is conducted on the black-box optimization benchmark test problems, which are capable of generating large-scale test instances. Numerical results on the new problems from CEC2013 and CEC2017 test suites, and the real-world application of rover trajectory planning demonstrate that the proposed approach achieves competitive performance compared to state-of-the-art methods. The adaptation behavior and the contribution of learning are also thoroughly analyzed.

The heightened autonomy and robust adaptability inherent in a multi-robot system have proven pivotal in disaster search and rescue, agricultural irrigation, and environmental monitoring. This study addresses the coordination of multiple robots for the surveillance of various key target positions within an area. This involves the allocation of target positions among robots and the concurrent planning of routes for each robot. To tackle these challenges, we formulate a unified optimization model addressing both target allocation and route planning. Subsequently, we introduce an adaptive memetic algorithm featuring dual-level local search strategies. This algorithm operates independently among and within robots to effectively solve the optimization problem associated with surveillance. The proposed method’s efficacy is substantiated through comparative numerical experiments and simulated experiments involving diverse scales of robot teams and different target positions.