Using Reinforcement Learning in a Game-like Setup for Automated Process Synthesis without Prior Process Knowledge

The present work uses reinforcement learning (RL) for automated flowsheet synthesis. The task of synthesizing a flowsheet is reformulated into a two-player game, in which an agent learns by self-play without prior knowledge. The hierarchical RL scheme developed in our previous work (Göttl et al., 2021b) is coupled with an improved training process. The training process is analyzed in detail using the synthesis of ethyl tert-butyl ether (ETBE) as an example. This analysis uncovers how the agent’s evolution is driven by the two-player setup.