Tstarbot-x: An Open-sourced And Comprehensive Study For Efficient League Training In Starcraft II Full Game

Abstract

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 succee

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhan2020tstarbot

Related papers

• SCC: An Efficient Deep Reinforcement Learning Agent Mastering The Game Of Starcraft II (2020)0.00
• Tstarbots: Defeating The Cheating Level Builtin AI In Starcraft II In The Full Game (2018)0.00
• An Introduction Of Mini-alphastar (2021)0.00
• Alphastar: An Evolutionary Computation Perspective (2019)15.13
• Applying Supervised And Reinforcement Learning Methods To Create Neural-network-based Agents For Playing Starcraft II (2021)0.00
• Macro Action Selection With Deep Reinforcement Learning In Starcraft (2018)9.92
• Efficient Reinforcement Learning For Starcraft By Abstract Forward Models And Transfer Learning (2019)8.60
• Starcraft II: A New Challenge For Reinforcement Learning (2017)0.00