Much of the renewed interest in the game stems from its connection with computing technology: not only because backgammon is being packaged as a hot new form of online gaming or because a PC is a tireless and always-available opponent, but because backgammon has become one of the success stories of research into artificial intelligence (AI).
US Players: Bovada Casino, Poker and Betting - $3750 Total Bonus - Click here..
Self-taught backgammon-playing computer programs are so good that they have overturned many of the assumptions previously held about how the game should be played and which are the best moves, especially in the opening phases of the game.
Any player who trains by regularly playing against a backgammon program, using moves suggested by the program itself, can learn to play at levels that were previously attained by only a few top players. Unlike the top chess-playing computers and computer programs, which tend to use brute-force tree searching and rely on massive amounts of computing power in a hybrid hardware/software platform, any PC can run a world-class backgammon program.
Hydra, which is the worlds most powerful chess-playing computer and has never been beaten, is a cluster computer based on 32 x 3.06GHz Xeon processors, each paired with its own FPGA (Field Programmable Gate Array) device and capable of evaluating 200 million moves per second.
It is able to look 18 moves ahead, which is six more than IBMs Big Blue. In contrast, the top backgammon programs, which are based on neural net techniques, will run happily on a bog-standard Pentium under Windows 95.
Learning by doing
Backgammon-playing programs are entirely self taught using the technique of reinforcement learning, which is one of the most promising avenues of research into artificial intelligence.
In essence, its no different from the way we train dogs, dishing out a reward when the animal does what we want it to and withholding the reward when it doesnt.
In AI, the trainee or agent, is a neural network, and it is the aim of the agent to maximise the total amount of reward it receives. An agent wont respond at all to a biscuit or a pat on the head, so the reward is a numerical one based on the agents most recent action.
What the agent must try to do is maximise the cumulative reward it receives for succeeding in its goal and not get hung up on the immediate reward for making one good decision.
The goal in any game is, of course, to win and its easy to score the outcome by awarding +1 points for a win, -1 points for losing and 0 points for a draw or uncompleted game.
An agent needs to understand the environment in which it operates and must know when it has achieved its goal, but in the case of backgammon this is incredibly simple.
A backgammon board is basically a one-dimensional race track split into 24 segments, with opponents racing in opposite directions and all checkers moving identically. A draw is impossible and the goal has been achieved when the agent gets all its checkers round the track before its opponent.
TC Ads is an interactive marketing company, specializing in performance based marketing solutions. To play backgammon online against more than 1.000.000 other players and participate in live tournaments in the largest backgammon room in the world click here now !
US Players: Bovada Casino, Poker and Betting - $3750 Total Bonus - Click here..