aidanscannell
Postdoctoral Researcher at Aalto University | Aalto Robot Learning Lab | Machine Learning Research Group | Finnish Center for Artificial Intelligence
Aalto UniversityHelsinki, Finland
Pinned Repositories
sfr
PyTorch implementation of Sparse Function-space Representation of Neural Networks
GPJax
Minimal Gaussian process library in JAX with a simple (custom) approach to state management.
iqrl
iQRL: implicitly Quantized Representations for Sample-efficient Reinforcement Learning
lane-detection
Lane and vehicle detection software for an autonomous vehicle.
ModeRL
Mode-constrained model-based-reinforcement learning in TensorFlow/GPflow
mogpe
Mixtures of Gaussian Process Experts in GPflow/TensorFlow
my-org-resume
Personal CV/Resume written in Org-mode with the LaTeX AltaCV template.
pilco-tensorflow
PILCO - Probabilistic Inference for Learning COntrol
reproducible-research-project-template
Template for writing reproducible machine learning papers
trajectory-optimisation-in-learned-multimodal-dynamical-systems
Trajectory optimisation in learned multimodal dynamical systems via latent-space collocation - JAX.
aidanscannell's Repositories
aidanscannell/GPJax
Minimal Gaussian process library in JAX with a simple (custom) approach to state management.
aidanscannell/iqrl
iQRL: implicitly Quantized Representations for Sample-efficient Reinforcement Learning
aidanscannell/reproducible-research-project-template
Template for writing reproducible machine learning papers
aidanscannell/PILCO
Implementation of PILCO: A Model-Based and Data-Efficient Approach to Policy Search
aidanscannell/ModeRL
Mode-constrained model-based-reinforcement learning in TensorFlow/GPflow
aidanscannell/phd-thesis
Bayesian Learning for Control in Multimodal Dynamical Systems | written in Org-mode
aidanscannell/simenvs
A collection of (simple) simulation environments for reinforcement learning in TensorFlow
aidanscannell/unc-mbrl
Investigating uncertainty quantification in model-based RL
aidanscannell/geoflow
Minimal library for geometric machine learning in TensorFlow (and GPflow).
aidanscannell/mbrl-under-uncertainty
aidanscannell/aidanscannell-hugo-academic
aidanscannell/aidanscannell.github.io
Personal Resume
aidanscannell/BNN-predictions
Improving predictions of Bayesian neural nets via local linearization, AISTATS 2021
aidanscannell/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
aidanscannell/Dotfiles
My personal dotfiles.
aidanscannell/flax
Flax is a neural network library for JAX that is designed for flexibility.
aidanscannell/garage
A toolkit for reproducible reinforcement learning research.
aidanscannell/GPflow
Gaussian processes in TensorFlow
aidanscannell/Grounded-Segment-Anything
Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
aidanscannell/home-robot
Mobile manipulation research tools for roboticists
aidanscannell/literate-dotfiles
My Mac OSX dotfiles in literate form using Emacs org-mode.
aidanscannell/mbrl-lib
Library for Model Based RL
aidanscannell/meta-dreamerv2
Mastering Atari with Discrete World Models
aidanscannell/miryoku_zmk
Miryoku is an ergonomic, minimal, orthogonal, and universal keyboard layout. Miryoku ZMK is the Miryoku implementation for ZMK.
aidanscannell/mosvgpe
aidanscannell/neural-tangents
Fast and Easy Infinite Neural Networks in Python
aidanscannell/paper-template
aidanscannell/paper-website-template
aidanscannell/tdmpc2
Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"
aidanscannell/transformers-metarl
Transformers are Meta-Reinforcement Learners - International Conference on Machine Learning (ICML) 2022