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

2017/12/08 by Ben Parr, Deepak Dilipkumar, Parr, Ben +3 · 1 voice
#cs.AI

paper · pdf · doi:10.48550/arxiv.1712.03280

Abstract

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% of the time.

Discussions

• Super Smash Bros. Melee: An “Untouchable” Agent [hn, 64 points, 26 comments]

Related

• Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning
• At Human Speed: Deep Reinforcement Learning with Action Delay
• Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning
• Identification of Play Styles in Universal Fighting Engine
• Suphx: Mastering Mahjong with Deep Reinforcement Learning