New answers tagged

0 votes

How many games will a “MENACE” tic tac toe computer take to train

To add to what Tassle said, I just tried training the AI against another copy of itself, and this produced slightly better results. I tried Increasing the number of beads taken from the matchbox on a ...
ACertainArchangel's user avatar
0 votes

Why we need at most $2n$ examples to determine an axis aligned rectangle

It's not really true the any sample of size 2n (all with positive label) can be used to determine the rectangle. Take for example the following sample $S$: $$ S=\{(\mathbf{x}_i, 1): \mathbf{x}_{i} = \...
Tran Khanh's user avatar
2 votes
Accepted

How many games will a “MENACE” tic tac toe computer take to train

Let me illustrate with a hand-wavy argument on a very simple game why convergence to optimal play might be very slow, and not even guaranteed, when training against a random opponent. Consider the ...
Tassle's user avatar
  • 2,522

Top 50 recent answers are included