Ensemble Reinforcement Learning: A Survey

Reinforcement learning (RL) has achieved state-of-the-art performance in many scientific and applied problems. However, some complex tasks still are difficult to handle using a single model and algorithm. The highly popular ensemble reinforcement learning (ERL) has become an important method to handle complex tasks with the advantage of combining reinforcement learning and ensemble learning (EL). ERL combines several models or training algorithms to fully explore the problem space and has strong generalization characteristics. This study presents a comprehensive survey on ERL to provide the readers with an overview of the recent advances and challenges. The background is introduced first. The strategies successfully applied in ERL are analyzed in detail. Finally, we outline some open questions and conclude by discussing some future research directions of ERL. This survey contributes to ERL development by providing a guide for future scientific research and engineering applications.

LAGA: A Learning Adaptive Genetic Algorithm for Earth Electromagnetic Satellite Scheduling Problem

Earth electromagnetic exploration satellites are widely used in many fields due to their wide detection range and high detection sensitivity. The complex environment and the proliferating number of satellites make management a primary issue. We propose a learning adaptive genetic algorithm (LAGA) for the earth electromagnetic satellite scheduling problem (EESSP). Control parameters are vital for evolutionary algorithms, and their sensitivity to the problem makes tuning parameters usually require a lot of effort. In the LAGA, we use a GRU artificial neural network model to control the parameters of variation operators. The GRU model can utilize online information to achieve adaptive adjustment of the parameters during population search. Moreover, a policy gradient-based reinforcement learning method is designed to update the GRU network parameters. By using an adaptive evolution mechanism in the algorithm, the LAGA can autonomously select crossover operators. Furthermore, a heuristic initialization method, an elite strategy, and a local search method are adopted in the LAGA to enhance the overall performance. The proposed algorithm can obtain a more optimal solution on the EESSP through sufficient experimental validations compared to the state-of-the-art algorithms.