GDC + [email protected] 2018 Session Scheduler

View, browse and sort the ever-growing list of GDC sessions by time, pass type, track, and format. With GDC Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App. Sessions do fill up, so please arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.

In order to best utilize Session Scheduler, please use the login credentials you've set up on this page as your login credentials on our GDC Mobile App. Your login credentials are the same as your registration login. You can download the app on iTunes or Google Play.

Building a Reinforcement Learning Agent in 'Starcraft 2' (Presented by NVIDIA)

Sponsor Speakers:

Miro Enev (Sr. Solution Architect Deep Learning, NVIDIA)

Eric Harper (Solutions Architect Deep Learning, NVIDIA)

Location: Room 3009, West Hall

Date: Friday, March 23

Time: 10:00am - 12:00pm

Pass Type: All Access, GDC Conference + Summits, GDC Conference, GDC Summits, Expo Plus, Audio Conference + Tutorial, Educators Summit, Indie Games Summit - Get your pass now!

Topic: Programming

Format: Sponsored Session

Vault Recording: Video

Audience Level: Intermediate

In this lab you will train a deep reinforcement learning agent to play Starcraft 2. The agent will train in Blizzard's Starcraft 2 Machine Learning environment and use DeepMind's Starcraft 2 Learning Environment (SC2LE) to communicate with the game engine in Python. You will implement deep reinforcement learning algorithms and test their effectiveness in minigames of increasing difficulty. SC2LE is designed so that AI will have to play similarly to a human. The AI can only see the units that are in its field of view and has to input commands at a rate that is comparable to human play. With AlphaGo recently beating the world's best Go players, Starcraft 2 is the next great challenge in AI and reinforcement learning.

Due to the enormous state and action spaces of Starcraft 2, NVIDIA GPUs are necessary for the challenge of training deep reinforcement agents to play Starcraft 2 at human expert levels.

Note, a laptop is required to attend this training.


In this lab, you will see how Deep Reinforcement Learning Agents can be trained to effectively play games at human level or above.

Intended Audience

Developers who are interested in leveraging AI bots to enable dynamic games

Creatives who want to see how AI can make human-like decisions

Project Managers to see how AI can change game design