aidanscannell

GPJax

Minimal Gaussian process library in JAX with a simple (custom) approach to state management.

reproducible-research-project-template

Template for writing reproducible machine learning papers

iqrl

iQRL: implicitly Quantized Reinforcement Learning

PILCO

Implementation of PILCO: A Model-Based and Data-Efficient Approach to Policy Search

ModeRL

Mode-constrained model-based-reinforcement learning in TensorFlow/GPflow

phd-thesis

Bayesian Learning for Control in Multimodal Dynamical Systems | written in Org-mode

simenvs

A collection of (simple) simulation environments for reinforcement learning in TensorFlow

unc-mbrl

Investigating uncertainty quantification in model-based RL

geoflow

Minimal library for geometric machine learning in TensorFlow (and GPflow).

mbrl-under-uncertainty

aidanscannell-hugo-academic

aidanscannell.github.io

Personal Resume

BNN-predictions

Improving predictions of Bayesian neural nets via local linearization, AISTATS 2021

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Dotfiles

My personal dotfiles.

flax

Flax is a neural network library for JAX that is designed for flexibility.

garage

A toolkit for reproducible reinforcement learning research.

GPflow

Gaussian processes in TensorFlow

Grounded-Segment-Anything

Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

home-robot

Mobile manipulation research tools for roboticists

literate-dotfiles

My Mac OSX dotfiles in literate form using Emacs org-mode.

mbrl-lib

Library for Model Based RL

meta-dreamerv2

Mastering Atari with Discrete World Models

miryoku_zmk

Miryoku is an ergonomic, minimal, orthogonal, and universal keyboard layout. Miryoku ZMK is the Miryoku implementation for ZMK.

mosvgpe

neural-tangents

Fast and Easy Infinite Neural Networks in Python

paper-template

paper-website-template

tdmpc2

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

transformers-metarl

Transformers are Meta-Reinforcement Learners - International Conference on Machine Learning (ICML) 2022