Research project
Deep reinforcement learning for wells
Planning well paths through 3D subsurface data with actor-critic methods.
2019–2020Research period
Project description
From the original project page. Results and time references describe that version of the work.
During my Freshman year of college, I created a new method for analyzing 3D subsurface data to pre-plan well paths. I implemented multiple DRL frameworks, including the Advantage Actor-Critic (A2C) framework. Our agent found optimal paths by maximizing oil and minimizing cost. Code and more information about the project are available on my GitHub below.