Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning
This work offers an incremental improvement in exploration efficiency for reinforcement learning agents in the domain of molecular design, potentially benefiting drug and material discovery.
This paper addresses the challenge of efficient exploration in the vast chemical search space for computer-aided molecular design using reinforcement learning. The authors propose a curiosity-inspired algorithm and demonstrate on three benchmarks that their 'curious agent' discovers better-performing molecules.
Computer-aided design of molecules has the potential to disrupt the field of drug and material discovery. Machine learning, and deep learning, in particular, have been topics where the field has been developing at a rapid pace. Reinforcement learning is a particularly promising approach since it allows for molecular design without prior knowledge. However, the search space is vast and efficient exploration is desirable when using reinforcement learning agents. In this study, we propose an algorithm to aid efficient exploration. The algorithm is inspired by a concept known in the literature as curiosity. We show on three benchmarks that a curious agent finds better performing molecules. This indicates an exciting new research direction for reinforcement learning agents that can explore the chemical space out of their own motivation. This has the potential to eventually lead to unexpected new molecules that no human has thought about so far.