William Guss

A language model programming library.

The code for my OpenAI Gym & Tensorflow tutorial.

The UC Berkeley CS61B class.

Old deep learning framework in C#.

Machine Learning

Slither reinforcement learning agent.

The Multi-Agent Reasoning script creates an interactive chatbot experience where multiple AI agents collaborate through a structured reasoning process to provide optimal answers.

An implementation of direct feeback alignment for tensorflow.

A website.

An article made for O'Reilley on the neural colorization paper by http://richzhang.github.io/colorization/

No description.

Lightweight coding agent that runs in your terminal

Hero is a modification of Project Malmo aimed at enabling high fidelity behavioral cloning in Minecraft.

The NetHack Learning Environment

Gmail JavaScript API

WIP on developing a plugin to make minecraft run on a headless EGL device.

A small project exploring the effectiveness of modeling and solving the n-body problem with neural networks.

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

Starter Kit for the NeurIPS 2019 MineRL Challenge

No description.

A C# Win32 console library providing high level access to ascii manipulation in the console including a GUI api.

A visualizer for the hardy-littlewood maximal function.

A visual studio code extension for viewing github issues.

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

GPU-acceleration of Nocturne via Madrona

The next version of AJS

Python XML Schema Bindings

This repo contains tutorials on OpenCV-Python library using new cv2 interface

Tensors and Dynamic neural networks in Python with strong GPU acceleration

No description.

Signal Processing based edge detection and auto-cropping framework

Modifications to the Minecraft base files to assist in compatibility between mods.

No description.

MineRL Gail!

TensorFlow documentation

Code for the CS294 deep reinforcment learning course taught at UC Berkeley.

Generalized Linear Models in Sklearn Style

Proximal Policy Optimization(PPO) Algorithm and its distributed implementation in Pytorch

Neural architecture selection theory project.

Graph based neural architecture search using reinforcement learning.

A brief exploration into bounded maximal constraints for Q learning.

Continuous hyperparameter representation for neural networks

Desktop/Android/HTML5/iOS Java game development framework

A toolkit for developing and comparing reinforcement learning algorithms.

No description.

Computation using data flow graphs for scalable machine learning

Minecraft environment for Open AI Gym, based on Microsoft's Malmo.

A distutils package for gnumpy and npmat

Demo showing neon and Nervana Cloud integration with OpenAI's RL-Gym

Stealth game for the Nar8 jam

A working resume collection.

A test game made using JavaLib

lol

g()()()()('al') → "gooooal"

Ascii stuff

Build your buildings and hide. Don