Temporal Difference Learning in Score-Four

نویسندگان

  • Matthew Hlavacek
  • Benedict Lim
  • John Ngo
چکیده

We have developed a machine-learning taught computer player for the game Score-Four, a three-dimensional variant of the aptly named Connect Four. This project was constructed at Northwestern University as a final project for the EECS 349: machine Learning course taught by Professor Bryan Pardo, where we applied temporal difference learning onto a neural network.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Control of Multivariable Systems Based on Emotional Temporal Difference Learning Controller

One of the most important issues that we face in controlling delayed systems and non-minimum phase systems is to fulfill objective orientations simultaneously and in the best way possible. In this paper proposing a new method, an objective orientation is presented for controlling multi-objective systems. The principles of this method is based an emotional temporal difference learning, and has a...

متن کامل

A Study on the Level of Learners' Readiness for Learning from the View Point of B.S. Students in Isfahan Medical University in 2001

Introduction. One of the basic human activities is learning and education. Indeed the role of education is to facilitate learning but many internal or external factors affect the learning process such as learners’ physical, affective and mental readiness. If we don’t pay attention to these factors, they will lead to a superficial learning and finally the trained and graduated students won't be...

متن کامل

Salvianolic Acid Improves Status Epilepticus and Learning and Memory Deficiency in Rat Model of Temporal Lobe Epilepsy

Background and Objective: Epilepsy is a long-lasting central nervous system disorder that is accompany with spontaneous seizures and insufficiency in learning and memory. Now drug treatment is the most common therapy but some patients do not research to suitable control of their seizures with current drugs. Hence, new treatment is needed to help those patients that are unaffected to existing dr...

متن کامل

The Effect of Alpha-Lipoic Acid on Learning and Memory Deficit in a Rat Model of Temporal Lobe Epilepsy

Introduction: Epilepsy is a chronic neurological disorder in which patients experience spontaneous recurrent seizures and deficiency in learning and memory. Although the most commonly recommended therapy is drug treatment, some patients do not achieve adequate control of their seizures on existing drugs. New medications with novel mechanisms of action are needed to help those patients whose sei...

متن کامل

The Educational Environment of Main Clinical Wards in Educational Hospitals Affiliated to Iran University of Medical Sciences: Learners' Viewpoints Based on DREEM Model

Introduction: DREEM (Dundee Ready Education Environment Measure) model is used as a diagnostic tool for assessing educational problems and effectiveness of educational changes as well as identifying the difference between real and optimum environments. This tool measures the teaching and learning environ-ment. The aim of this study was to investigate the viewpoints of residents and interns of f...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012