0 Replies - 1377 Views - Last Post: 07 November 2016 - 08:58 AM

#1 modi123_1  Icon User is offline

  • Suitor #2
  • member icon

Reputation: 14036
  • View blog
  • Posts: 56,156
  • Joined: 12-June 08

[link] DeepMind and Blizzard to release StarCraft II as an AI research

Posted 07 November 2016 - 08:58 AM

Well this is pretty nifty.. I wonder how long until this API is available for everyone.



DeepMind is on a scientific mission to push the boundaries of AI, developing programs that can learn to solve any complex problem without needing to be told how. Games are the perfect environment in which to do this, allowing us to develop and test smarter, more flexible AI algorithms quickly and efficiently, and also providing instant feedback on how we’re doing through scores.
An agent that can play StarCraft will need to demonstrate effective use of memory, an ability to plan over a long time, and the capacity to adapt plans based on new information. Computers are capable of extremely fast control, but that doesn’t necessarily demonstrate intelligence, so agents must interact with the game within limits of human dexterity in terms of “Actions Per Minute”. StarCraft’s high-dimensional action space is quite different from those previously investigated in reinforcement learning research; to execute something as simple as “expand your base to some location”, one must coordinate mouse clicks, camera, and available resources. This makes actions and planning hierarchical, which is a challenging aspect of Reinforcement Learning.
We’ve worked closely with the StarCraft II team to develop an API that supports something similar to previous bots written with a “scripted” interface, allowing programmatic control of individual units and access to the full game state (with some new options as well). Ultimately agents will play directly from pixels, so to get us there, we’ve developed a new image-based interface that outputs a simplified low resolution RGB image data for map & minimap, and the option to break out features into separate “layers”, like terrain heightfield, unit type, unit health etc.

Is This A Good Question/Topic? 0
  • +

Page 1 of 1