Ankita Shukla
Papers
1
Total Citations
2
H-Index
1
About
Ankita Shukla is a computational scientist whose research sits at the intersection of molecular simulation, reinforcement learning, and statistical mechanics. Her most notable contribution is the development of a novel framework that combines reinforcement learning with adaptive steered molecular dynamics to efficiently map low free energy transition pathways between molecular states. By integrating Jarzynski’s equality and the stiff-spring approximation, her work provides a principled, sampling-based approach to estimating free energy landscapes—a fundamental challenge in biophysics and materials science. This innovative methodology, published in 2022, has already garnered attention for its potential to accelerate the study of rare events in complex systems, such as protein folding or ligand binding. Shukla’s work exemplifies how robotics-inspired planning algorithms can be repurposed to solve problems in molecular dynamics, opening new avenues for automated exploration of conformational spaces. Her research is particularly relevant for students and researchers interested in applying machine learning to physical sciences, demonstrating how reinforcement learning can serve as a powerful tool for navigating high-dimensional energy surfaces.
Research Focus
Key Achievements
Top Papers
- 1