(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original AlphaStar is the AI proposed by DeepMind to play StarCraft II. JAIR = Journal of Artificial Intelligence Research.

Reinforcement learning framework to accelerate research

We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enhanced algorithm achieves 100% win rates on SMAC-V1 and superior performance on SMAC-V2.

Python framework for rapid development of Starcraft 2 AI bots

Communication using GNN in MARL

We reproduced DeepMind's results and implement a meta-learning (MLSH) agent which can generalize across minigames.

StarCraft 2 Imitation Learning

(AAAI'2019) The codes, models, logs, and data for an extended paper of the original paper "On Reinforcement Learning for Full-length Game of StarCraft". AAAI = AAAI Conference on Artificial Intelligence.

StarCraft 2 AI Workshop

A StarCraft 2 agent for harvesting resources

Golang client for the Starcraft II protocol

Applying the DQN-Agent from keras-rl to Starcraft 2 Learning Environment and modding it to to use the Rainbow-DQN algorithms.

(TG'2023) Official code for the paper "Revisiting of AlphaStar" (previously called "Rethinking of AlphaStar"). It compares the raw interface with the human interface in the architecture of AlphsStar. TG = Transactions on Games

(TG'2021) Code for paper "Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning". TG = Transactions on Games.

Rule based AI for StarCraft 2 Minigames

A creative (generative) bot, implemented using Generative Adversarial Networks, for the RL environment released by DeepMind for the adversarial strategy game, StarCraft II.

Simple {scripts for ctf`s and challenges/python irc bot/automating stuff etc.}

The best starcraft 2 bot in the entire galaxy.

Winner Starcraft II bot with convolutional neural networks

StarCraft 2 via Type Based Heirarchial Multi Agent Reinforcement Leanring