# TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game

arXiv: https://arxiv.org/abs/2011.13729 · HTML: https://mlsanity.com/paper/2011.13729/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 27 Nov 2020.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 21 of 21)

- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2112.11701/) (2021)
- [Neural Categorical Priors for Physics-Based Character Control](https://mlsanity.com/paper/2308.07200/) (2023)
- [Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models](https://mlsanity.com/paper/2308.15143/) (2023)
- [A Survey on Self-play Methods in Reinforcement Learning](https://mlsanity.com/paper/2408.01072/) (2024)
- [Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems](https://mlsanity.com/paper/2102.07659/) (2021)
- [Gym-μRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning](https://mlsanity.com/paper/2105.13807/) (2021)
- [On Efficient Reinforcement Learning for Full-length Game of StarCraft II](https://mlsanity.com/paper/2209.11553/) (2022)
- [AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning](https://mlsanity.com/paper/2308.03526/) (2023)
- [SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks](https://mlsanity.com/paper/2410.16024/) (2024)
- [An Empirical Study on Google Research Football Multi-agent Scenarios](https://mlsanity.com/paper/2305.09458/) (2023)
- [AVA: Attentive VLM Agent for Mastering StarCraft II](https://mlsanity.com/paper/2503.05383/) (2025)
- [On games and simulators as a platform for development of artificial intelligence for command and control](https://mlsanity.com/paper/2110.11305/) (2021)
- [TacticCraft: Natural Language-Driven Tactical Adaptation for StarCraft II](https://mlsanity.com/paper/2507.15618/) (2025)
- [HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making](https://mlsanity.com/paper/2509.12927/) (2025)
- [Rethinking of AlphaStar](https://mlsanity.com/paper/2108.03452/) (2021)
- [Learning Heterogeneous Agent Cooperation via Multiagent League Training](https://mlsanity.com/paper/2211.11616/) (2022)
- [Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II](https://mlsanity.com/paper/2109.12691/) (2021)
- [Relative Policy-Transition Optimization for Fast Policy Transfer](https://mlsanity.com/paper/2206.06009/) (2022)
- [Cooperative-Competitive Team Play of Real-World Craft Robots](https://mlsanity.com/paper/2602.21119/) (2026)
- [Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts](https://mlsanity.com/paper/2606.30092/) (2026)

## Abstract (arXiv)

StarCraft, one of the most difficult esport games with long-standing history of professional tournaments, has attracted generations of players and fans, and also, intense attentions in artificial intelligence research. Recently, Google's DeepMind announced AlphaStar, a grandmaster level AI in StarCraft II that can play with humans using comparable action space and operations. In this paper, we introduce a new AI agent, named TStarBot-X, that is trained under orders of less computations and can play competitively with expert human players. TStarBot-X takes advantage of important techniques introduced in AlphaStar, and also benefits from substantial innovations including new league training methods, novel multi-agent roles, rule-guided policy search, stabilized policy improvement, lightweight neural network architecture, and importance sampling in imitation learning, etc. We show that with orders of less computation scale, a faithful reimplementation of AlphaStar's methods can not succeed and the proposed techniques are necessary to ensure TStarBot-X's competitive performance. We reveal all technical details that are complementary to those mentioned in AlphaStar, showing the most sensitive parts in league training, reinforcement learning and imitation learning that affect the performance of the agents. Most importantly, this is an open-sourced study that all codes and resources (including the trained model parameters) are publicly accessible via urlhttps://github.com/tencent-ailab/tleagueprojpage. We expect this study could be beneficial for both academic and industrial future research in solving complex problems like StarCraft, and also, might provide a sparring partner for all StarCraft II players and other AI agents.