maitchison Goto Github PK

arxiv-sanity-preserver

Web interface for browsing, search and filtering recent arxiv submissions

atari-5

Repo for the paper "Atari-5: Distilling the Arcade Learning Environment down to Five Games"

bootstrap

Discounting based on uncertanty estimates from bootstrap samples rathern than timesteps.

cfdtoybox

cfractal

Fast fractal explorer written in c++

classifier-pipeline

Exports tracked animals through thermal vision.

com

coup

Coup

cptv-download

Bulk extract thermal video recordings from a Cacophony Project API server

crypto

Collection of algorithms from MATH220.

gated-linear-networks

gitignore

A collection of useful .gitignore templates

glengine

COSC367 assignment

gym

A toolkit for developing and comparing reinforcement learning algorithms.

idris2

A purely functional programming language with first class types

mousemaze

Experiments on history based methods for reinforcement learning on medium to large mazes.

omega

Calculate the first few bits of the omega constant.

perceptron

Examples from Machine Learning by Stephen Marsland

phasic-policy-gradient

Code for the paper "Phasic Policy Gradient"

phd-readings

Notes on readings and courses for PhD

pong

ppo

Example implemention of the Proximal Policy Optimization algorithm

python-cptv

Python parser for Cacophony Project Thermal Video (CPTV) files

pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.

raytracer

A raytracer written in C++ with GI and SSS.

rtg

Rescue the General Game

sc2_il

StarCraft II Bot by Imitation Learning

stable-baselines3-dna

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

summerscholar2018

Repo for work done at ANU Summer Scholarship 2018 (Feature Reinforcement Learning)

sutton

Exercises for Richard Sutton and Andrew Barto's Reinforcement Learning book.