A joint paper that outlines the environment, and reports initial baseline results on the mini-games, supervised learning from replays, and the full 1v1 ladder game against the built-in AI. A series of simple RL mini-games to allow researchers to test the performance of agents on specific tasks. An open source version of DeepMind’s toolset, PySC2, to allow researchers to easily use Blizzard’s feature-layer API with their agents. A dataset of anonymised game replays, which will increase from 65k to more than half a million in the coming weeks. 
This includes the release of tools for Linux for the first time.
A Machine Learning API developed by Blizzard that gives researchers and developers hooks into the game. That is why we, along with our partner Blizzard Entertainment, are excited to announce the release of SC2LE, a set of tools that we hope will accelerate AI research in the real-time strategy game StarCraft II. Testing our agents in games that are not specifically designed for AI research, and where humans play well, is crucial to benchmark agent performance. To do this, we design agents and test their ability in a wide range of environments from the purpose-built DeepMind Lab to established games, such as Atari and Go. DeepMind's scientific mission is to push the boundaries of AI by developing systems that can learn to solve complex problems.
0 kommentar(er)
