Automated Materials Design and Discovery Using Reinforcement Learning

Studying how to automate material synthesis and discovery by training a Deep Reinforcement Learning system to plan and carry out chemical synthesis experiments to gather data and find efficient pathways to making new or known materials.

METHODS | reinforcement-learning | LSTM | LRCN | MARL | MDP

WEBPAGE: | http://chemgymrl.com

In early 2019 the lab began a new collaboration sponsored by the National Research Council – UW Collaboration Centre (NUCC) on AI/Cybersecurity/IoT. This is a new organization set-up to initial research collaboration between NRC staff researchers and UW PIs. I am one of the first faculty to be a part of this endeavour and to receive funding for my work. With Dr. Isaac Tamblyn (NRC) and Dr. Colin Bellinger (NRC), our project studies how to automate material synthesis and discovery by training a Deep Reinforcement Learning system to plan and carry out chemical synthesis experiments to gather data and find efficient pathways to making new or known materials.

To find out more, take a look at the current framework to carry out your own experiments or contribute to the framework: chemgymrl.com

Problem Description

The main idea is described most recently in our paper (Bellinger et al., 2022) with some great high-level summary and motivation. This paper also outlines a modification to the standard single-action RL framework, to divide actions into two parts containing an costly observation choice in addition to the usual action which affects the world.

Our Papers on ChemGymRL

  1. Balancing Information with Observation Costs in Deep Reinforcement Learning
    Bellinger, Colin, Drozdyuk, Andriy, Crowley, Mark, and Tamblyn, Isaac
    In Canadian Conference on Artificial Intelligence 2022
  2. Scientific Discovery and the Cost of Measurement – Balancing Information and Cost in Reinforcement Learning
    Bellinger, Colin, Drozdyuk, Andriy, Crowley, Mark, and Tamblyn, Isaac
    In 1st Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE) 2022
  3. Amrl
    Active Measure Reinforcement Learning for Observation Cost Minimization: A framework for minimizing measurement costs in reinforcement learning
    Bellinger, Colin, Coles, Rory, Crowley, Mark, and Tamblyn, Isaac
    In Canadian Conference on Artificial Intelligence 2021
  4. Reinforcement Learning in a Physics-Inspired Semi-Markov Environment
    Bellinger, Colin, Coles, Rory, Crowley, Mark, and Tamblyn, Isaac
    In Canadian Conference on Artificial Intelligence 2020