TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Peng Sun, Xinghai Sun, Lei Han, Jiechao Xiong, Qing Wang, Bo Li, Yang, Zheng, Ji Liu, Yongsheng Liu, Han Liu, Tong Zhang

TL;DR
This paper introduces two full-game StarCraft II AI agents, TStarBot1 and TStarBot2, capable of defeating high-level built-in AI opponents, advancing the state of AI in complex strategic environments.
Contribution
It presents the first public AI agents that can beat the built-in StarCraft II AI in full game scenarios, using deep reinforcement learning and rule-based hierarchical strategies.
Findings
TStarBot1 and TStarBot2 defeat AI levels 1-10 in full game.
Agents outperform cheating AI levels with unfair advantages.
First public demonstration of full-game StarCraft II AI defeating built-in opponents.
Abstract
Starcraft II (SC2) is widely considered as the most challenging Real Time Strategy (RTS) game. The underlying challenges include a large observation space, a huge (continuous and infinite) action space, partial observations, simultaneous move for all players, and long horizon delayed rewards for local decisions. To push the frontier of AI research, Deepmind and Blizzard jointly developed the StarCraft II Learning Environment (SC2LE) as a testbench of complex decision making systems. SC2LE provides a few mini games such as MoveToBeacon, CollectMineralShards, and DefeatRoaches, where some AI agents have achieved the performance level of human professional players. However, for full games, the current AI agents are still far from achieving human professional level performance. To bridge this gap, we present two full game AI agents in this paper - the AI agent TStarBot1 is based on deep…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Artificial Intelligence in Games · Explainable Artificial Intelligence (XAI)
