samuelstanton Goto Github PK

backpack

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

bayesopt-hd

Bayesian optimization tailored for high dimensional objective functions

biopython

Official git repository for Biopython (originally converted from CVS)

botorch

Bayesian optimization in PyTorch

conformal-bayesopt

Bayesian optimization with conformal coverage guarantees

dm_control

The DeepMind Control Suite and Package

gauche

A Library for Gaussian Processes in Chemistry

gnosis

Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.

gpytorch

A highly efficient and modular implementation of Gaussian Processes in PyTorch

grasp

Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH

gym-maze

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.

home

Personal Webpage

hydra

Hydra is a framework for elegantly configuring complex applications

hydra-ray-demo

Demonstration of how to structure a project with Hydra for easy deployment with Ray

lambo

Code to reproduce experiments in "Accelerating Bayesian Optimization for Protein Design with Denoising Autoencoders" (Stanton et al 2022)

mbbl

mbpo

Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

model-zoo

out-of-the-box probabilistic regression models

oac-explore

Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)

proximal-exploration

PyTorch implementation for our paper "Proximal Exploration for Model-guided Protein Sequence Design"

pypdb

A Python API for the RCSB Protein Data Bank (PDB)

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch_sac

PyTorch implementation of Soft Actor-Critic (SAC)

samuelstanton.github.io

personal blog

svg

On the model-based stochastic value gradient for continuous reinforcement learning

upcycle

reusable code snippets from previous projects