Guodong Chen

TL;DR: Zhang et al. as mentioned in this paper proposed a rank loss function for acquiring a superior intertask mapping, with an evolutionary path-based representation model for optimization instance, and an analytical solution of affine transformation for bridging the gap between two distinct problems is derived from the proposed rank loss.

TL;DR: The results show that the proposed GLSADE method can achieve higher net present value (NPV) and better convergence speed in comparison with the traditional evolutionary algorithm and other surrogate-assisted optimization methods for production-optimization problems.

TL;DR: The results show that the proposed EHSDE method is effective and efficient for most benchmark functions and for the production optimization problem compared with other state-of-the-art algorithms.

TL;DR: In this paper, a model-free deep reinforcement learning (DRL) algorithm is used to train a stochastic policy that maps reservoir states to well control variables and an action-value function that estimates the objective value of the current policy.

TL;DR: An efficient multiobjective evolutionary algorithm (MOEA) to effectively deal with computationally expensive simulation-based optimization problems is designed that incorporates a Pareto-rank-learning scheme with surrogate-assisted infill criterion and provides a classifier first that can enhance the accuracy in high dimensions and reduce computational complexity.