scholarly journals Deep Reinforcement Learning of Transition States

2021 ◽  
Author(s):  
Jun Zhang ◽  
Yao-Kun Lei ◽  
Zhen Zhang ◽  
Xu Han ◽  
Maodong Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Reinforcement Learning ◽  
Transition State ◽  
Chemical Reaction ◽  
Reaction Mechanisms ◽  
Md Simulations ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Chemical Reaction Mechanisms

Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach, called RL‡, to automatically unravel chemical reaction mechanisms. In RL‡, locating the transition state of a...

scholarly journals A Machine Learning Approach to Calculate Electronic Couplings between Quasi-Diabatic Molecular Orbitals: The Case of DNA

2021 ◽  
Author(s):  
Xin Bai ◽  
Xin Guo ◽  
Linjun Wang
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Complex Interaction ◽  
Learning Approach ◽  
Molecular Electronic ◽  
Base Pairs ◽  
Nonadiabatic Coupling ◽  
Representative Sequence ◽  
Machine Learning Approach ◽  
Efficient Machine

Diabatization of one-electron states in flexible molecular aggregates is a great challenge due to the presence of surface crossings between molecular orbital (MO) levels and the complex interaction between MOs of neighboring molecules. In this work, we present an efficient machine learning approach to calculate electronic couplings between quasi-diabatic MOs without the need of nonadiabatic coupling calculations. Using MOs of rigid molecules as references, the MOs that can be directly regarded to be quasi-diabatic in molecular dynamics are selected out, state tracked, and phase corrected. On the basis of this information, artificial neural networks are trained to characterize the structure-dependent onsite energies of quasi-diabatic MOs and the inter-molecular electronic couplings. A representative sequence of DNA is systematically studied as an illustration. Smooth time evolution of electronic couplings in all base pairs is obtained with quasi-diabatic MOs. Especially, our method can calculate electronic couplings between different quasi-diabatic MOs independently, and thus possesses unique advantages in many applications.

scholarly journals Reinforcement Learning-Based Television White Space Database

2021 ◽  
Vol 18 (2(Suppl.)) ◽  
pp. 0947
Author(s):  
Armie E. Pakzad ◽  
Raine Mattheus Manuel ◽  
Jerrick Spencer Uy ◽  
Xavier Francis Asuncion ◽  
Joshua Vincent Ligayo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
High Frequency ◽  
Learning Approach ◽  
Very High Frequency ◽  
Machine Learning Technique ◽  
Secondary Users ◽  
Machine Learning Approach ◽  
Learning Technique ◽  
Very High

Television white spaces (TVWSs) refer to the unused part of the spectrum under the very high frequency (VHF) and ultra-high frequency (UHF) bands. TVWS are frequencies under licenced primary users (PUs) that are not being used and are available for secondary users (SUs). There are several ways of implementing TVWS in communications, one of which is the use of TVWS database (TVWSDB). The primary purpose of TVWSDB is to protect PUs from interference with SUs. There are several geolocation databases available for this purpose. However, it is unclear if those databases have the prediction feature that gives TVWSDB the capability of decreasing the number of inquiries from SUs. With this in mind, the authors present a reinforcement learning-based TVWSDB. Reinforcement learning (RL) is a machine learning technique that focuses on what has been done based on mapping situations to actions to obtain the highest reward. The learning process was conducted by trying out the actions to gain the reward instead of being told what to do. The actions may directly affect the rewards and future rewards. Based on the results, this algorithm effectively searched the most optimal channel for the SUs in query with the minimum search duration. This paper presents the advantage of using a machine learning approach in TVWSDB with an accurate and faster-searching capability for the available TVWS channels intended for SUs.

Sign in / Sign up

Export Citation Format

Share Document