Next: MDP description
Previous: MDPs with a very
TD-Gammon uses a neural
network with 198 inputs. For each position and for each color
there are four inputs:
State encoding TD-Gammon
If no piece is present then all four inputs are false.
- equals true if there is at least one piece present.
- equals true if there are at least two pieces present.
- equals true if there are at least three pieces present.
- has a value of
if there are at least four pieces present.
additional inputs encode the number of pieces that were "taken"
for each color. Each one has a value of
where n is
the number of eaten pieces. Two other inputs encode the number of
pieces removed. Each one has a value of
is the number of pieces removed. Two last boolean inputs encode
for each player whether it is his turn currently.