How and why games behave the way they do

Ever wondered why games behave the way they do? Or why games are smart enough to show you who’s the master? How they calculate your rankings among the world’s best?

Take a look truly "behind the scenes" and discover what guys like the Machine Learning and Perception Group at Microsoft Research Ltd, Cambridge, UK do for your games.

Applied Games

"(…) to leverage the methods of approximate probabilistic inference for addressing relevant applications both in recreational games and in abstract decision games played in the real world."

If that sounds too strange, just take a closer look at their various projects:

Behaviour Capture

  • Drivatar in Forza Motorsport: "(…) to create human-like computer opponents to race against."
  • Learning to Fight: "(…) using reinforcement learning algorithms to automatically learn a policy for computer games. (…) apply reinforcement learning to the problem of finding good policies for an agent in a commercial fighting game."

Xbox Live

  • TrueSkill for ranking and matchmaking in Xbox 360 Live.

Trust and Reputation

  • Cheaters and Liars: "(…) build models that make it possible to infer who are perpetrators and who are reliable sources of information from the feedback data (in virtual online gaming communities)."

Interactive Dynamics

{One of my posts at "香港 (Hong Kong) 地區 Xbox 討論區" dated "10-03-2006, 4:38PM"}

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: