Deephive: A Reinforcement Learning Approach for Automated Discovery of Swarm-Based Optimization Policies

We present an approach for designing swarm-based optimizers for the global optimization of expensive black-box functions. In the proposed approach, the problem of finding efficient optimizers is framed as a reinforcement learning problem, where the goal is to find optimization policies that require a few function evaluations to converge to the global optimum. The state of each particle within the swarm is defined as its current position and function value within a design space, and the particles learn to take favorable actions that maximize the reward, which is based on the final value of the objective function. The proposed approach is tested on 50 benchmark optimization functions and compared to the performance of other global optimization strategies. Furthermore, the generalization capabilities of the trained particles on the four categories of optimization benchmark functions are investigated. The results show superior performance compared to the other optimizers, desired scaling when the dimension of the functions is varied, and acceptable performance even when applied to unseen functions. On a broader scale, the results show promise for the rapid development of domain-specific optimizers.