In-Depth Look at the AI Behind Age of Rivals, A Strategy Card Game

Overview

This is meant to be an in-depth look at how the AI makes decisions in Age of Rivals, a strategy card game.  This AI is considered to be pretty strong by players, so hopefully this will be useful to anyone approaching the challenge of building a competitive AI opponent for a strategy game.  

The Game

To anyone unfamiliar with Age of Rivals, a quick video overview can be found at https://www.youtube.com/watch?v=S2WhRlh2tqI.

Briefly, Age of Rivals is a card drafting game in which 2 players compete to build the best ancient civilization.  Players draft 16 cards to form their city over the course of 3 rounds and then select their best 8 cards for a final showdown round.  Each round also consists of a War phase during which cards attempt to knock each other out and a Scoring phase used to earn the points that ultimately determine the winner.  City cards each have various stats and a special ability that can influence the outcome of the game.

Goal of the System

The initial goal of the AI was to provide a good learning experience for new players, at which point players would transition into playing multiplayer exclusively.  But as we realized that there was a significant number of players who wanted to play single player, I kept improving the AI to play at a higher level.  

During the course of any AoR game, there are basically two kinds of decisions a player must make:

Drafting

To make the first decision (what to draft), the AI scores each card across 17 different categories.  For each category, a function examines the card and the current state of the game and returns a score between 0 and 1.  Then the AI weights each of these results, averages them into an overall score, and drafts the card with the best overall score.  Weights for the categories range from 1 (not very important) to 20 (very important).  

The 17 categories are: