DeepAI AI Chat
Log In Sign Up

Automatically Reinforcing a Game AI

07/27/2016
by   David L. St-Pierre, et al.
1

A recent research trend in Artificial Intelligence (AI) is the combination of several programs into one single, stronger, program; this is termed portfolio methods. We here investigate the application of such methods to Game Playing Programs (GPPs). In addition, we consider the case in which only one GPP is available - by decomposing this single GPP into several ones through the use of parameters or even simply random seeds. These portfolio methods are trained in a learning phase. We propose two different offline approaches. The simplest one, BestArm, is a straightforward optimization of seeds or parame- ters; it performs quite well against the original GPP, but performs poorly against an opponent which repeats games and learns. The second one, namely Nash-portfolio, performs similarly in a "one game" test, and is much more robust against an opponent who learns. We also propose an online learning portfolio, which tests several of the GPP repeatedly and progressively switches to the best one - using a bandit algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/25/2020

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

We present JueWu-SL, the first supervised-learning-based artificial inte...
05/13/2019

Ludii - The ludemic General Game System

While current General Game Playing (GGP) systems facilitate useful resea...
06/15/2021

Rinascimento: searching the behaviour space of Splendor

The use of Artificial Intelligence (AI) for play-testing is still on the...
10/31/2022

DanZero: Mastering GuanDan Game with Reinforcement Learning

Card game AI has always been a hot topic in the research of artificial i...
06/29/2018

AI in Game Playing: Sokoban Solver

Artificial Intelligence is becoming instrumental in a variety of applica...
08/04/2020

Inducing game rules from varying quality game play

General Game Playing (GGP) is a framework in which an artificial intelli...
05/30/2017

Multi-Labelled Value Networks for Computer Go

This paper proposes a new approach to a novel value network architecture...