Sam Toyer Claim this profile

The MAGICAL benchmark suite for robust imitation learning (NeurIPS 2020)

Source for Action Schema Networks paper (AAAI'18)

Multi-task imitation learning algorithms for the MAGICAL benchmark

Fork of the caffe2keras converter from @MarcBS (UNMAINTAINED)

No description.

Inverse reinforcement learning experiments from variational discriminator bottleneck (VDB) paper (https://openreview.net/pdf?id=HyxPx3R9tm)

DMMs for human pose forecasting. Fork of clinicalml/structuredinference (disassociated by Github because it was private for a while)

My project for the Semester 2, 2015 offering of COMP2560 (Studies in Advanced Computing R&D) at ANU

Yet another Tinychat replacement for the LessWrong study hall

Regressing joints for fun and profit

TF-Agents is a library for Reinforcement Learning in TensorFlow

The most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.

Intuitive timetable builder for the Australian National University.

LLM tool for discovering interesting things about a paper by chaining through the papers that cite it

Mastering Diverse Domains through World Models

My code and reports for the S1, 2015 offering of COMP2550 (R&D Methods) at ANU

Demonstration data for the MAGICAL imitation learning benchmark suite

No description.

Moss summarizer

Export pages from a Hatta wiki to HTML

mmap vs read for sequential reads of a big file (48GiB)

Repository for "StrongREJECT for Empty Jailbreaks" paper

The simplest, fastest repository for training/finetuning medium-sized GPTs.

No description.

:alarm_clock: AI conference deadline countdowns

No description.

A Python SDK for Vertex AI, a fully managed, end-to-end platform for data science and machine learning.

The open-source repo for docs.github.com

The Web framework for perfectionists with deadlines.

Sokoban environment for OpenAI Gym

MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (TPAMI 2020)

Toolbox of models, callbacks, and datasets for AI/ML researchers.

PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.

Official Open Source code for "Masked Autoencoders As Spatiotemporal Learners"

A pleasant note-taking platform.

Aligning AI With Shared Human Values (ICLR 2021)

This repository provides text game simulators for research purposes.

Jiminy Cricket Environment (NeurIPS 2021)

The Piranha computer algebra system.

american fuzzy lop (copy of the source code for easy access)

The Arcade Learning Environment (ALE) -- a platform for AI research.

The Fast Downward domain-independent classical planning system

Code for the paper "Generative Adversarial Imitation Learning"

The color picker skill is a simple skill where alexa asks you to pick a color and responds back with the color you chose, when you ask it what is your favorite color. This sample Alexa Skill is written in Python and demonstrates the use of session attributes.

A PyTorch implementation of FQF, IQN and QR-DQN.

Python with the scientific stack, compiled to WebAssembly.

A PyTorch implementation of SimCLR based on ICML 2020 paper "A Simple Framework for Contrastive Learning of Visual Representations"

Bootstrap models of human sub-rationality by using feedback modalities with different levels of reliability

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A Django admin theme using Twitter Bootstrap. It doesn't need any kind of modification on your side, just add it to the installed apps.

RAD: Reinforcement Learning with Augmented Data

Public release of ENGN4528 project (vision at ANU) with @KuangyiXing

🐍 The official Python client library for Google's discovery based APIs.

rllab's viskit with some added features

Open Source Differentiable Computer Vision Library for PyTorch

q - Run SQL directly on CSV or TSV files

Reinforcement Learning in PyTorch

Pytorch implementation of Stable Opponent Shaping (https://openreview.net/pdf?id=SyGjjsC5tQ).

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

Pymunk is a easy-to-use pythonic 2d physics library that can be used whenever you need 2d rigid body physics from Python

No description.

A system for parallel and distributed Python that unifies the ML ecosystem.

Simple example of implementing a new Tensorflow operation and its gradient in C++.

A toolkit for developing and comparing reinforcement learning algorithms.

My copy of rllab. master branch has possibly-breaking changes, minor-fixes branch has some really obvious fixes that I should probably PR into original rllab

No description.

No description.

No description.

LaTeX Notes from the Fall 2018 version of CS294-149: AGI Safety and Control

Holistically-Nested Edge Detection

website source for the computational media lab

No description.

Plumbum: Shell Combinators

FaceAlign is a tool that can align a set of images containing faces

A lightweight wrapper around theano for rapid-prototyping of models

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

No description.

Code repository for Convolutional Pose Machines

HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.

My Caffe fork with various custom nonsense (see branches)

Helps working with singletons - things like global settings that you want to edit from the admin site.

Caffe with heatmap regression & spatial fusion layers. Useful for any CNN image position regression task.

Public facing notes page

Introduction to Statistical Machine Learning at ANU

Math extension for Python-Markdown