Pinned Repositories
easyrl-pytorch
PPO implementation in PyTorch
fluxschedule
Open source code of Flux Schedule. 2018 published App Store description: https://appadvice.com/app/flux-speed-schedules/1336300102. See Youtube link for demo.
genprop
Mini DL Library with eager automatic differentiation. Supports backpropagation over a dynamically built graph.
gpt-2
Increased the efficiency of GPT-2 by one pass/token per prompt. See https://github.com/openai/gpt-2/pull/119. Code for the paper "Language Models are Unsupervised Multitask Learners"
gptransfer
Experiments modifying GPT-2 for classification, in Google Colab. One-click reproducible
HearthEnv
A Hearthstone environment for reinforcement learning agents, subclassing OpenAI/Gym. Supports human input, and includes a default agent.
Legible_Baselines
Commented versions of OpenAI's Baselines code
MSCRED
Concise, modular implementation of Multi-Scale Convolutional Recurrent Encoder Decoder: https://arxiv.org/abs/1811.08055
ShrinkPad
A Windows 10 app that allows the user to draw strokes, but with a catch: The strokes will intelligently resize themselves by a certain percentage after a certain amount of time has passed without pen input, or after one of several other conditions. Developed solely as a prototype app to encourage implementation in Microsoft OneNote and other pen input apps. Fully functional.
votelbot
A Telegram bot for voice-to-voice conversations with AI built with Vocode
albertwujj's Repositories
albertwujj/MSCRED
Concise, modular implementation of Multi-Scale Convolutional Recurrent Encoder Decoder: https://arxiv.org/abs/1811.08055
albertwujj/gptransfer
Experiments modifying GPT-2 for classification, in Google Colab. One-click reproducible
albertwujj/votelbot
A Telegram bot for voice-to-voice conversations with AI built with Vocode
albertwujj/albertwujj.github.io
Human Philosophy blog
albertwujj/ext2fs
ext2 File System in C, from inodes to terminal commands, with WSU's KC Wang’s textbook
albertwujj/fluxschedule
Open source code of Flux Schedule. 2018 published App Store description: https://appadvice.com/app/flux-speed-schedules/1336300102. See Youtube link for demo.
albertwujj/genprop
Mini DL Library with eager automatic differentiation. Supports backpropagation over a dynamically built graph.
albertwujj/gpt-2
Increased the efficiency of GPT-2 by one pass/token per prompt. See https://github.com/openai/gpt-2/pull/119. Code for the paper "Language Models are Unsupervised Multitask Learners"
albertwujj/docker-marlo
U.S. localization fork of ikeyasu's docker-marlo
albertwujj/minerl-1
MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
albertwujj/rlscience
practicing applying and modifying RL
albertwujj/send-a-damned-message
Simple text-based game
albertwujj/ShrinkPad
A Windows 10 app that allows the user to draw strokes, but with a catch: The strokes will intelligently resize themselves by a certain percentage after a certain amount of time has passed without pen input, or after one of several other conditions. Developed solely as a prototype app to encourage implementation in Microsoft OneNote and other pen input apps. Fully functional.
albertwujj/minerl
Expert Transfer Learning plays Minecraft, using Pytorch. Back-tracks in expert demonstrations to determine exactly where items are located in field of view.
albertwujj/angryclawsts
Slay the Spire Mod. Make Claw duplicate like Anger.
albertwujj/Ape-X
PyTorch Implementation of Distributed Prioritized Experience Replay(Ape-X)
albertwujj/boots
albertwujj/Burrows-Wheeler
Implementation of Burrows-Wheeler data compression algorithm. Project from Princeton COS 226.
albertwujj/lightning
Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.
albertwujj/malmo
albertwujj/malmo-1
Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:
albertwujj/manim
Using this Mathematical ANIMation engine and rewriting Euclidean proofs in 2D form.
albertwujj/minrl
RL algorithms, minimal
albertwujj/moviesite
albertwujj/obstacle-tower-pytorch-rainbow
PyTorch & Rainbow for Obstacle Tower Challenge
albertwujj/old_basic_rl
Vanilla Policy Gradient, DQN in Tensorflow
albertwujj/Rainbow
Rainbow: Combining Improvements in Deep Reinforcement Learning
albertwujj/sparse_attention
Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
albertwujj/suttonrl
albertwujj/tictac
TicTacToe React tutorial