A couple of days ago, this discussion about the difficulty of getting an AI to play Mario Kart started up on a post I made. I decided to start doing some research into gaming/speedrunning AI and it has ultimately led to me staring at a screen watching an AI try to complete 1-1 in Super Mario Bros for the past two days.
The AI is a simple Lua script that runs in an emulator, but it was designed specifically for Super Mario World. There are some issues I would like to straighten out with it, as it can not complete 1-1 yet. Basically, the AI presses random buttons until it starts to move to the right. Moving to the right will give it a progressively higher score, and if it stops or dies, it will reset and try again. It then takes the best attempts and expands on them.
I've been observing some of the intricacies of how the AI functions, and I think that with some tweaks, it could actually learn to complete quite a few of the levels in Mario.
The source code is here. It runs in the FCEUX emulator and is very easy to set up. It'd be cool to turn this into a little project and expand on it, because it really is fascinating to watch and I don't think it will be that difficult to do.
I see what you're saying, but wouldn't using lap time as an indicator account for that? If the strategy for corner 1 left it at a disadvantage for corner 2, the overall lap time would reflect that, correct?
Either way, I totally get why brute-force trial/error works better in a 2D setting. SMW has orders of magnitude less possibilities, between directional limitations, fewer controls, and one fewer dimension of travel.