Presentation is loading. Please wait.

Presentation is loading. Please wait.

A Naïve Treatment of Self- Contained Digital Sentience in Pursuit of Erudition in a Stochastic Game By Robert Brady Computer Systems Research 2004-2005.

Similar presentations


Presentation on theme: "A Naïve Treatment of Self- Contained Digital Sentience in Pursuit of Erudition in a Stochastic Game By Robert Brady Computer Systems Research 2004-2005."— Presentation transcript:

1 A Naïve Treatment of Self- Contained Digital Sentience in Pursuit of Erudition in a Stochastic Game By Robert Brady Computer Systems Research 2004-2005

2 ABSTRACT This tech-lab project deals with the field of Artificial Intelligence or more specifically, Machine Learning. I am designing an agent/environment for the card game of bridge. After it learns the rules, I will run simulations where it decides on its own what the best play is. The level of play for the agent will increase as the year continues because it will look up past decisions in its history to determine what the best bid or play is in a current state of the environment.

3 Introduction Machine learning is a concentrated part of the field of Artificial Intelligence. It deals with agent/environment systems where the agent learns from past decisions to determine a current-state action.

4 Background Programs such as GIB and Bridge Baron are past attempts to create a bridge-playing agent. These programs lack a learning part, though, unlike the project I am undertaking.

5 Algorithms Algorithms and processes considered: Minimax Backtracking Search Alpha-Beta Pruning Neural Networking Actual Design: Minimax with alpha-beta pruning

6 Preliminary Testing ● To the right represents an early version of the program where it determined that the best action for each player would be to pass. ● This isn't the action an expert player would take, but it is not unreasonable.

7 Future Testing The program will soon be tested against the skills of players in this high school beginning with the students in my tech-lab class and expanding outward to the school's bridge club.

8 Research and Citations Fred Gitelman – I contacted him as a professional programmer and an expert bridge player. He advised me on how to develop the algorithm for my learning agent in the beginning stages of the year. Artificial Intelligence A Modern Approach Second Edition by S. Russell and P. Norvig – I used this book to compare different types of algorithms to decide which was the right one for my project.


Download ppt "A Naïve Treatment of Self- Contained Digital Sentience in Pursuit of Erudition in a Stochastic Game By Robert Brady Computer Systems Research 2004-2005."

Similar presentations


Ads by Google