
It has been developed for the Texas Hold’em variant of poker, in which each player is dealt two ‘hole’ cards, and all players share an additional five cards that are dealt to the board.
From the seven cards known to them, each player makes the best five-card hand possible and pits this against other players.
In recent times, Texas Hold’em has received the attention of academics and computer programmers due to the challenges of probabilities and decision-making in the face of uncertainty that players confront when playing the game
Fellows explained that the private information in each player’s hole cards breaks the usual method of ‘game tree search’ that is used to solve chess and backgammon challenges using computer systems.
“Unlike chess, poker is a game of chance,” said Fellows, whose usual job involves designing research studies and analysing data for the Department of Geriatrics at UC San Diego and who describes himself as a ‘mediocre’ poker player.
“Players don’t know what cards they will be dealt, or what cards will be dealt to the board,” he said.
“While techniques for dealing with chance have been well established in the context of other games such as backgammon, what sets poker apart is that it is a game of imperfect information.”
According to Fellows, the field of computer poker has made great strides in recent years, as artificially intelligent programs have improved from being easily beaten by children six years ago to being a challenge to professional poker players today.
Fell Omen 2 is 50 megabytes in size and can be downloaded from http://thefell.googlepages.com/poker. The program is expected to aid human players improving their poker skills and their understanding of game theory.