Imitation-Guided Reinforcement Learning with Adaptive Sampling and Expert Knowledge for Real-Time Well Control Optimization

Summary Deep reinforcement learning (DRL) has been increasingly applied to real-time well control optimization but remains hindered by low sampling efficiency and weak early-stage exploration. Even though neural networks excel in learning, they lack search capacity, while evolutionary algorithms (EAs) provide strong global search but no learning capability. In this paper, we propose an adaptive dual-experience replay framework that integrates the advantages of EAs and reinforcement learning (RL) to improve the efficiency and accuracy of real-time well control optimization. High-quality samples are generated through EAs and used to guide the policy learning of the DRL agent via imitation learning (IL), effectively realizing the warm start of policy learning. Meanwhile, DRL’s autonomous exploration capability is preserved, enabling a collaborative optimization process that combines experience transfer and self-directed learning. An adaptive sampling strategy further enhances training by dynamically adjusting the contributions of experiences from the EA and DRL buffers, improving policy stability and generalization. This study focuses specifically on injection/production rate and bottomhole pressure (BHP) optimization in benchmark reservoir models. Experimental results show that the proposed method outperforms baseline approaches in net present value (NPV) and convergence speed. Additionally, robustness tests demonstrate that the trained policy maintains strong performance when directly applied to unseen scenarios. Notably, it achieves comparable performance to the state-of-the-art soft actor-critic (SAC) algorithm using only half the training episodes, underscoring its potential for intelligent oilfield development.