Reinforcement Learning for Molecular Design Guided by Quantum Mechanics
12. července 2020
Řečníci
Gregor N. C. Simm
Řečník · 0 sledujících
Robert Pinsler
Řečník · 0 sledujících
Jose Hernandez-Lobato
Řečník · 0 sledujících
O prezentaci
Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. A limitation of existing approaches is that they work with molecular graphs and thus ignore the location of atoms in space, which restricts them to (1) generating single organic molecules and (2) heuristic reward functions. To address this, we present a novel RL formulation for molecular design in 3D space, thereby extending the class of molecules that can be built. Our reward function is directly based on fundamental physical properties such as the energy, which we approximate via fast quantum-chemical calculations. To enable progress towards designing molecules in 3D space, we introduce MolGym, an RL environment comprising several molecular design tasks alongside with baselines. In our experiments, we show that our agent can efficiently learn to solve these tasks from scratch by working in a translation and rotation invariant state-action space.Automating molecular design using deep reinforcement learning (RL) holds the promise of accelerating the discovery of new chemical compounds. A limitation of existing approaches is that they work with molecular graphs and thus ignore the location of atoms in space, which restricts them to (1) generating single organic molecules and (2) heuristic reward functions. To address this, we present a novel RL formulation for molecular design in 3D space, thereby extending the class of molecules that can…
Kategorie
Chemie
Kategorie · 175 prezentací
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
Zhlédnout později
Yufei Wang, …
Harmonic Decompositions of Convolutional Networks
Zhlédnout později
Anonymous Survey System and Methodology to Enable COVID-19 Surveillance
Zhlédnout později
Regularized Optimal Transport is Ground Cost Adversarial
Zhlédnout později
Bayesian Deep Learning and a Probabilistic Perspective of Model Construction - Part 4
Zhlédnout později
