Samuel Stanton's Projects
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
Bayesian optimization tailored for high dimensional objective functions
A standard library for biological research.
Official git repository for Biopython (originally converted from CVS)
Bayesian optimization in PyTorch
Bayesian optimization with conformal coverage guarantees
The DeepMind Control Suite and Package
A Library for Gaussian Processes in Chemistry
Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.
A highly efficient and modular implementation of Gaussian Processes in PyTorch
Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH
A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.
Personal Webpage
Hydra is a framework for elegantly configuring complex applications
Demonstration of how to structure a project with Hydra for easy deployment with Ray
Code to reproduce experiments in "Accelerating Bayesian Optimization for Protein Design with Denoising Autoencoders" (Stanton et al 2022)
Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"
out-of-the-box probabilistic regression models
Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)
A collection of objective functions and black box optimization algorithms related to proteins and small molecules
PyTorch implementation for our paper "Proximal Exploration for Model-guided Protein Sequence Design"
A Python API for the RCSB Protein Data Bank (PDB)
Tensors and Dynamic neural networks in Python with strong GPU acceleration
PyTorch implementation of Soft Actor-Critic (SAC)
personal blog
On the model-based stochastic value gradient for continuous reinforcement learning
reusable code snippets from previous projects