DeepAI AI Chat
Log In Sign Up

Reinforced dynamics for enhanced sampling in large atomic and molecular systems. I. Basic Methodology

by   Linfeng Zhang, et al.
Princeton University

A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning. There are two major components in this new approach. Like metadynamics, it allows for an efficient exploration of the configuration space by adding an adaptively computed biasing potential to the original dynamics. Like deep reinforcement learning, this biasing potential is trained on the fly using deep neural networks, with data collected judiciously from the exploration and an uncertainty indicator from the neural network model playing the role of the reward function. Applications to the full-atom, explicit solvent models of alanine dipeptide and tripeptide show some promise for this new approach.


Deep Learned Path Planning via Randomized Reward-Linked-Goals and Potential Space Applications

Space exploration missions have seen use of increasingly sophisticated r...

Deep neural network for Wannier function centers

We introduce a deep neural network (DNN) model that assigns the position...

Cluster Generation via Deep Energy-Based Model

We present a new approach for the generation of stable structures of nan...

Automated discovery of a robust interatomic potential for aluminum

Atomistic molecular dynamics simulation is an important tool for predict...

A Deep Reinforcement Learning Approach for Dynamically Stable Inverse Kinematics of Humanoid Robots

Real time calculation of inverse kinematics (IK) with dynamically stable...

N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials

We describe N-body networks, a neural network architecture for learning ...