TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game

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 reinforcement learning over a flat action structure, and the AI agent TStarBot2 is based on hard-coded rules over a hierarchical action structure. Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting. To the best of our knowledge, this is the first public work to investigate AI agents that can defeat the built-in AI in the StarCraft II full game.

arXiv commentadd link for source code

References in corpus (3)

• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
• Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement Learning and Multi-task Reinforcement Learning

Cited by in corpus (17)

• Deep Reinforcement Learning for Cyber Security
• A Survey of Deep Reinforcement Learning in Video Games
• Hierarchical Decision Making by Generating and Following Natural Language Instructions
• SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
• TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
• Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation
• Hierarchical Reinforcement Learning for Multi-agent MOBA Game
• Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning
• Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning
• On Reinforcement Learning for Full-length Game of StarCraft
• An Introduction of mini-AlphaStar
• Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
• Arena: a toolkit for Multi-Agent Reinforcement Learning
• Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
• Gym-$\mu$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
• Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction
• Rethinking of AlphaStar