The field of optimization and control for smart systems is rapidly evolving, with a focus on developing innovative solutions to complex problems. Recent research has explored the application of reinforcement learning, genetic algorithms, and other optimization techniques to real-world challenges such as smart orchards, energy trading, and electric bus charging scheduling. A key direction in this field is the development of adaptive and interpretable methods that can handle uncertainty and multiple objectives. Notable papers in this area include: An adaptive experience-based discrete genetic algorithm for multi-trip picking robot task scheduling in smart orchards, which proposes an innovative approach to optimization in smart orchards. Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids, which introduces a systematic approach to ensuring constraint satisfaction in reinforcement learning. Safe and Sustainable Electric Bus Charging Scheduling with Constrained Hierarchical DRL, which develops a novel framework for optimizing electric bus charging schedules under uncertainty. GRAND: Guidance, Rebalancing, and Assignment for Networked Dispatch in Multi-Agent Path Finding, which proposes a hybrid method for task scheduling in multi-agent settings. Multi-Agent Reinforcement Learning for Intraday Operating Rooms Scheduling under Uncertainty, which applies multi-agent reinforcement learning to optimize operating room scheduling.