I would be interested in seeing the learning process for pacman further. I guess the algorithm just ran for a couple of iterations. Also, could we run an experiment with more complicated games, like doom? There also is an obvious way to count, namely the number of killed enemies. Chess? Maybe even some poker?
I will have to read that paper.
Also, could we run an experiment with more complicated games, like doom? There also is an obvious way to count, namely the number of killed enemies.
There is an obvious way to count, yes, but can it be easily located in the raw RAM of a running Doom instance? That's the point here, automatically inferring a measure of progress from somewhere in the raw binary blob.
If you have to explicitly define a reward counter, then you're just doing normal reinforcement-learning or AI kinda stuff, and you might as well go use a non-joke agent like AIXI-MC (already pl...
"Pretty simple" algorithm playing games quite impressively.
http://www.youtube.com/watch?v=xOCurBYI_gY
First, this is awesome - enjoy!
Paper here http://www.cs.cmu.edu/~tom7/mario/mario.pdf
One interesting observation made by Tom Murphy is that the AI found and exploited playable bugs in the game not (commonly) known to human players. I think it's a good example to have available suggesting what a really smart AI might look for to win.