Kind: captions
Language: en
this is a game of chess
played by two ai engines each far better
at chess than any human on earth
the question i had is what happens when
you let these machines battle it out on
an infinite chessboard with infinite
pieces
each move calculated and performed on an
8x8 subset that in isolation is a
totally legal position with two kings
but in the big picture is just a tiny
subset of a much bigger game
where each checkmate destroys the king
and the deserted pieces move on in
search of another neighboring victim
pieces get captured and sacrificed in
other words the usual game of chess but
on a much bigger board
the play is extended arbitrarily
outwards but here we focus on just this
subset of about 6 000 squares
on the bottom is the counter showing the
number of kings and checkmate victories
let me mention some details
the boards are initialized with the
middle game position from one of 30 000
famous grandmaster games including
magnus carlson bobby fischer kasparov
spas kital karpov and so on
the selection of which 8x8 subset to use
for computing the next move is made
randomly among all the boards that have
legal chest positions
optimizing the selection process
something that could be formulated as a
reinforcement learning problem and will
make this meta game of infinite chess
very interesting
in fact there are fascinating questions
here about the generalizability of ai
engines far beyond the scale and the
constraints of the game they were
trained on
chess is just a game
but when you start to remove the
constraints and increase the scale it
becomes something else
something more like the game of life
played on an infinite chessboard
[Music]
you