2. Deep Blue
A chess computer
program
Chinook
A computer program that
plays checkers
Chess On PC’s
A chess computer
program
TD-Gammon
A computer backgammon
program
02
01
04
03
3. Deep Blue (Chess Computer)
Humans were the strongest chess entities on the planet for centuries. Even in the
1980s, it seemed laughable that a computer could ever defeat the strongest human
players. Then in 1997, it happened—a computer defeated the world champion. Which
computer, you ask? Deep Blue.
Deep Blue was a chess computer developed by IBM. It is famous for defeating the
chess world champion, GM Garry Kasparov, in their 1997 match. Deep Blue's victory was
viewed as a symbolic testament to the rise of artificial intelligence—a victory for
machine versus man.
The Deep Blue was created by Feng-hsiung Hsu in 1985. In 1989 Hsu and other
colleagues joined the IBM team to fully develop Deep Blue.
5. The Evolution of Artificial Intelligence In Chess Engines
Chess is a two-player
strategy board game
played on a checkered
board with 64 squares
arranged in an 8×8 square
grid.
Artificial Intelligence is a
revolution in itself with
the numerous feats of
accomplishments that it
has been able to achieve.
The use of AI in the real
world and real-life
scenarios is ample.
Chess has gained
tremendous popularity,
and it is leading to a
revolutionary trend due to
more people getting
involved with chess at the
time of this global
pandemic.
CHESS PC’S
ON
6. Chess on PC’s
Computer chess applications, whether
implemented in hardware or software, utilize
different strategies than humans to choose
their moves: they use heuristic methods to
build, search and evaluate trees representing
sequences of moves from the current position
and attempt to execute the best such sequence
during play.
8. CHINOOK
Chinook is a computer program that plays checkers
(also known as draughts). It was developed
between the years 1989 to 2007 at the University of
Alberta, by a team led by Jonathan Schaeffer and
consisting of Rob Lake, Paul Lu, Martin Bryant, and
Norman Treloar. The program's algorithms include
an opening book which is a library of opening
moves from games played by checkers
grandmasters; a deep search algorithm; a good
move evaluation function; and an end-game
database for all positions with eight pieces or
fewer. All of Chinook's knowledge was programmed
by its creators, rather than learned using an
artificial intelligence system.
9. CHINOOK
Chinook's program algorithm includes an
opening book, a library of opening moves
from games played by grandmasters; a deep
search algorithm; a good move evaluation
function; and an end-game database for all
positions with eight pieces or fewer. The
linear handcrafted evaluation function
considers several features of the game
board, including piece count, kings count,
trapped kings, turn, runaway checkers
(unimpeded path to be kinged), and other
minor factors. All of Chinook's knowledge
was programmed by its creators, rather than
learned with artificial intelligence.
11. TD-GAMMON
TD-Gammon is a computer backgammon program
developed in 1992 by Gerald Tesauro at IBM's
Thomas J. Watson Research Center. Its name comes
from the fact that it is an artificial neural net
trained by a form of temporal-difference learning,
specifically TD-lambda.
TD-Gammon achieved a level of play just slightly
below that of the top human backgammon players
of the time. It explored strategies that humans had
not pursued and led to advances in the theory of
correct backgammon play.
12. TD-Gammon
TD learning is a combination of Monte Carlo ideas
and Dynamic Programming ideas. Similar to Monte
Carlo, TD methods can learn directly from raw
experience without a model of the environment’s
dynamics. Similar to dynamic programming, TD
methods update estimates based in part on other
learned estimates without waiting for final outcome.
In layman terms, it can be said that TD is a method
in which learning takes place after each interaction
(or maybe a few interactions) with the environment.
This is in contrast to Monte Carlo learning where
learning takes place only at the end of an episode.