CS297 Proposal

"Bluff" with AI

TINA PHILIP (talk2tinaphilip@gmail.com)

Advisor: Dr. Chris Pollett

Description:

The goal of this project is to build an AI that learns how to play Bluff. Bluff is a multi-player card game in which each player makes a sequence of decisions based on a partially-observed game state that evolves under uncertainty. The back bone of the implementation is a neural network with back-propagation. The network is made of a single neuron, possessing a single byte of intelligence. The neuron has "weights" and a "threshold"; the neuron "fires" when the value of the activation function computed over the current input exceeds the current threshold. In game terms, using the current score and the number of aces on hand the neuron decides if to draw another card or to stay. The threshold (the neuron's memory) is adjusted as the game proceeds, using back-propagation.

Schedule:

Deliverables:

The full project will be done when CS298 is completed. The following will be done by the end of CS297:

1. Notation to represent the game. Find a good algorithm for permutation of cards

2. Code a human only Bluff game.

3. Code a simple AI player to play Bluff.

4. Read about strategies used in Poker for AI players.

5. CS297 Report

References:

[1] Hurwitz, Evan, and Tshilidzi Marwala. "Learning to bluff." Systems, Man and Cybernetics, 2007. ISIC. IEEE International Conference on. IEEE, 2007.

[2] Darse Billings. "Algorithms and Assessment in Computer Poker, " Ph.D. Dissertation, 2006, University of Alberta, Edmonton, Alta., Canada. AAINR22991.

[3] Russell, Stuart, Peter Norvig, and Artificial Intelligence. "A modern approach."Artificial Intelligence. Prentice-Hall, Egnlewood Cliffs 25 (1995): 27.