O'Reilly logo

AI Game Programming Wisdom 4 by Steve Rabin

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

7.6A Practical Guide to Reinforcement Learning in First-Person Shooters

Michelle McPartland—University of Queensland

michelle@itee.uq.edu.au

The notion that bots could learn how to play a game, particularly one with the complexities of a modern first-person shooter (FPS), might appear to be wishful thinking, but it can actually be achieved using a class of algorithms known as reinforcement learning (RL). FPS bots are generally rule based and look at the information available to them about their environment and internal state to decide what actions they should take. As such, most FPS bots fall into the action-selection paradigm; that is, they select an action to perform from a predetermined list.

RL provides an action-selection model that is well ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required