Parallel Automatic History Matching Algorithm Using Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based method for parallel automatic history matching in reservoir simulation, enabling multiple solutions and significant speed improvements through concurrent environment learning.

Contribution

It reformulates history matching as a Markov Decision Process, allowing reinforcement learning to find multiple solutions in parallel with deep neural networks.

Findings

Enables parallel processing of history matching tasks.

Uses reinforcement learning with neural networks for reservoir simulation.

Achieves significant speed-up in solution finding.

Abstract

Reformulating the history matching problem from a least-square mathematical optimization problem into a Markov Decision Process introduces a method in which reinforcement learning can be utilized to solve the problem. This method provides a mechanism where an artificial deep neural network agent can interact with the reservoir simulator and find multiple different solutions to the problem. Such formulation allows for solving the problem in parallel by launching multiple concurrent environments enabling the agent to learn simultaneously from all the environments at once, achieving significant speed up.