1.3k citations
- Lawrence Berkeley National LaboratoryUS185 papers
- University of California, BerkeleyUS86 papers
- Kavli Energy NanoScience InstituteUS35 papers
- Advanced Light Source12 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Columbia UniversityUS8 papers
- Weizmann Institute of ScienceIL8 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR6 papers
- Foundry (United Kingdom)GB6 papers
- National Institute for Materials ScienceJP6 papers
- Technical University of MunichDE6 papers
- University of PennsylvaniaUS6 papers
Showing 2019 · cond-mat.stat-mechShow all
3 papers · 2 filters
cond-mat.stat-mech2019★ 66 cited
Learning to grow: control of material self-assembly using evolutionary reinforcement learning
Stephen Whitelam, Isaac Tamblyn
We show that neural networks trained by evolutionary reinforcement learning can enact efficient molecular self-assembly protocols. Presented with molecular simulation trajectories,…
cond-mat.stat-mech2019★ 24 cited
Evolutionary reinforcement learning of dynamical large deviations
Stephen Whitelam, Daniel Jacobson, Isaac Tamblyn
We show how to calculate the likelihood of dynamical large deviations using evolutionary reinforcement learning. An agent, a stochastic model, propagates a continuous-time Monte Ca…
cond-mat.stat-mech2019★ 24 cited
Direct evaluation of dynamical large-deviation rate functions using a variational ansatz
Daniel Jacobson, Stephen Whitelam
We describe a simple form of importance sampling designed to bound and compute large-deviation rate functions for time-extensive dynamical observables in continuous-time Markov cha…