# Deep Reinforcement Learning of Transition States

arXiv: https://arxiv.org/abs/2011.06700 · HTML: https://mlsanity.com/paper/2011.06700/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Accurate transition state generation with an object-aware equivariant elementary reaction diffusion model](https://mlsanity.com/paper/2304.06174/) (2023)
- [Reinforcement learning of rare diffusive dynamics](https://mlsanity.com/paper/2105.04321/) (2021)
- [3DReact: Geometric deep learning for chemical reactions](https://mlsanity.com/paper/2312.08307/) (2023)
- [React-OT: Optimal Transport for Generating Transition State in Chemical Reactions](https://mlsanity.com/paper/2404.13430/) (2024)
- [Probing reaction channels via reinforcement learning](https://mlsanity.com/paper/2305.17531/) (2023)
- [Pay Attention to What You Need](https://mlsanity.com/paper/2307.13365/) (2023)
- [Estimating Reaction Barriers with Deep Reinforcement Learning](https://mlsanity.com/paper/2407.12453/) (2024)
- [ASTEROID: A Spatiotemporal Information Transformer for Forecasting Multi-Step Time Series of Molecular Dynamics](https://mlsanity.com/paper/2606.17668/) (2026)

## Abstract (arXiv)

Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach (RL^ddag) to automatically unravel chemical reaction mechanisms. In RL^ddag, locating the transition state of a chemical reaction is formulated as a game, where a virtual player is trained to shoot simulation trajectories connecting the reactant and product. The player utilizes two functions, one for value estimation and the other for policy making, to iteratively improve the chance of winning this game. We can directly interpret the reaction mechanism according to the value function. Meanwhile, the policy function enables efficient sampling of the transition paths, which can be further used to analyze the reaction dynamics and kinetics. Through multiple experiments, we show that RLddag can be trained tabula rasa hence allows us to reveal chemical reaction mechanisms with minimal subjective biases.