Nintendo Super Smash Bros. Melee: An "Untouchable" Agent

12/08/2017
by   Ben Parr, et al.
0

Nintendo's Super Smash Bros. Melee fighting game can be emulated on modern hardware allowing us to inspect internal memory states, such as character positions. We created an AI that avoids being hit by training using these internal memory states and outputting controller button presses. After training on a month's worth of Melee matches, our best agent learned to avoid the toughest AI built into the game for a full minute 74.6

READ FULL TEXT
research
05/20/2023

A Measure of Explanatory Effectiveness

In most conversations about explanation and AI, the recipient of the exp...
research
10/28/2021

NetDAM: Network Direct Attached Memory with Programmable In-Memory Computing ISA

Data-intensive applications like distributed AI-training may require mul...
research
01/18/2019

Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators

Machine learning advances have afforded an increase in algorithms capabl...
research
08/24/2023

Language as Reality: A Co-Creative Storytelling Game Experience in 1001 Nights using Generative AI

In this paper, we present "1001 Nights", an AI-native game that allows p...
research
03/20/2022

Does DQN really learn? Exploring adversarial training schemes in Pong

In this work, we study two self-play training schemes, Chainer and Pool,...
research
09/12/2023

Defining the Entropy and Internal Energy of a Monetary Schelling model through the Energy States of Individual Agents

This work investigates a modified Schelling model within the scope and a...
research
04/27/2018

How does the AI understand what's going on

Most researchers regard AI as a static function without memory. This is ...

Please sign up or login with your details

Forgot password? Click here to reset