junkilee

starcraft-ai

codellama

Inference code for CodeLlama models

pysc2

StarCraft II Learning Environment

toybox-rs

Rust packages and for Toybox; separately versioned from Python code.

.vim

my .vim directory

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

awesome-causality-algorithms

An index of algorithms for learning causality with data

awesome-causality-data

A data index for learning causality.

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

simple_baselines

Simplified and Modified OpenAI Baselines Implementation

coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

distper

Distributed Priortized Experience Replay

distributed_reinforcement_learning

implementation of distributed reinforcement learning with distributed tensorflow

gym

A toolkit for developing and comparing reinforcement learning algorithms.

icp-block-mdp

Invariant Causal Prediction for Block MDPs

junkilee.github.io

Jun Ki Lee's Webpages

KoAlpaca

KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델

latex-yearly-planner

Digital planner for Supernote and ReMarkable // Support Ukraine 🇺🇦 https://www.comebackalive.in.ua/

llama-recipes

Examples and recipes for Llama 2 model

MinAtar

obsidian-day-planner

An Obsidian plugin for day planning and managing pomodoro timers from a task list in a Markdown note.

obsidian-full-calendar

Keep events and manage your calendar alongside all your other notes in your Obsidian Vault.

py-vgdl

A video game description language (VGDL) built on top pf pygame.

ray

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

SC2-RL

Reinforcement Learning for StarCraft II

simple_rl

A simple framework for experimenting with Reinforcement Learning in Python.

smac

SMAC: The StarCraft Multi-Agent Challenge

spinningup

An educational resource to help anyone learn deep reinforcement learning.

stable-baselines3

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

Toybox

The Machine Learning Toybox for testing the behavior of autonomous agents.