Monte-Carlo Tree Search is a promising technique that is revolutionizing board game AI. In this interview, find out how MCTS can be applied to The Octagon Theory, a mobile game which combines challenges similar to Othello or Go. What's necessary to build a competitive AI with probabilistic search techniques? How do you take into account opponent models into the process?
How does a small team of two programmers embrace change and build an AI that's fun to play against? In this interview with Kenneth Harder from BetaDwarf, you'll find out how the AI was iteratively made to be more challenging yet easy to understand by the player. You'll also learn about the techniques used to implement third-person tactical action AI with tight constraints in Unity.
In this masterclass with Alexander Shafranov, winner of the Capture The Flag competition with an HTN planner, you'll learn about plan compilation to C++ using a JSHOP2-inspired architecture. Find out how to reduce time spent planning for team and individual coordination using domain specific compiled code rather than an interpreted solution.
This tutorial explains in detail how write AI to flank an enemy. It's a fascinating problem than involves terrain representation, analysis, and reasoning. Learn about the simplest tricks in the book, for example solutions based on vector algebra using known landmarks as reference points, as well as more advanced techniques too that involve multiple layers of single-source search and tactical pathfinding!
In this interview with Emil "AngryAnt" Johansen, you'll learn about applying behavior trees to a problem reminiscent of RTS games, in particular a dodgeball scenario. Emil will share insights from the creation of those trees and the recent release of his Behave 2 tool for Unity.
In this this interview with Tom Betts, you'll learn how to generate convincing British countrysides (where it's fun being hunted by robots). You'll learn about the algorithms behind the biomes for the different island types, the high-level AI director that oversees the game, as well as other aspects of the enemy AI in Sir You Are Being Hunted.
It's all hands on deck for this interview about the AI in Card Hunter with Tess Snider. As well as covering the essential elements of a card-based board game AI, you'll learn how a modular component-based architecture allowed for a reusable decision logic that could deal with new cards easily, and how the team scaled the Java-based implementation to handle thousands of concurrent users.
This post-mortem interview with Mika Vehkala digs into the AI used to create the living and breathing world of HITMAN: ABSOLUTION. In particular, you'll learn about the underlying knowledge representation for the stealth behaviors, in particular propagation of information. You'll also hear about the tactical reasoning and positioning for enemies, and how it all ties together into this AAA system.
In this interview with Casper Friis Farsøe, you'll learn the details behind the AI in EXPEDITIONS: CONQUISTADOR, a game that received praise for its enemy behaviors and their tactical combat. You'll hear how the team's development methodology helped drive the architecture for the AI, and how that's reflected in game with great results.
In this more advanced tutorial, you'll find out more in depth about building more efficient AI algorithms using OpenCL. What techniques are necessary to get the best performance out of the hardware? This broadcast will cover compute-friendly pathfinding as well as voxel-based visibility algorithms.