In plain words: An AI reads character positions straight from the game's memory and presses controller buttons to dodge attacks, trained on a month of matches. It avoided the toughest built-in computer opponent for a full minute 74.6% of the time.
Abstract · Nintendo Super Smash Bros. Melee: An "Untouchable" Agent
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.
Ben Parr, Deepak Dilipkumar, Yuan Liu
arXiv:1712.03280 · cs.AI · submitted Dec 8, 2017
abstract · pdf · html
> The major limitation of our project was the opposing player. Of course, we would have preferred training against human players who play Melee professionally.
An alternative training method could be through the use of the 20XX hack pack [0], a mod of Super Smash Bros Melee that adds, among many useful features, an improved AI. Here's a video of the AI from release 4.05 in action: https://www.youtube.com/watch?v=rzl5NXV5bHQ
The built-in SSBM AI is very noticeably different from competitive play, and the 20XX AI makes significant steps toward more human-like competitive play. It would be interesting to see the results if trained on these AI.
[0] https://smashboards.com/threads/the-20xx-melee-training-hack...