Machine Learning, Game Play, and Go

✍ Scribed by Stoutamire D.

Tongue: English
Leaves: 90
Category: Library

No coin nor oath required. For personal study only.

✦ Synopsis

1991 — 90 p.
На англ. языке.

The game of go is an ideal problem domain for exploring machine learning: it is easy to define and there are many human experts, yet existing programs have failed to emulate their level of play to date. Existing literature on go playing programs and applications of machine learning to games are surveyed. An error function based on a database of master games is defined which is used to formulate the learning of go as an optimization problem. A classification technique called pattern preference is presented which is able to automatically derive patterns representative of good moves; a hashing technique allows pattern preference to run efficiently on conventional hardware with graceful degradation as memory size decreases.

✦ Subjects

Информатика и вычислительная техника;Искусственный интеллект

📜 SIMILAR VOLUMES

Learning to Play: Reinforcement Learning

📁 Learning to Play: Reinforcement Learning and Games

✍ Aske Plaat 📂 Library 📅 2020 🏛 Springer International Publishing;Springer 🌐 English

<p>In this textbook the author takes as inspiration recent breakthroughs in game playing to explain how and why deep reinforcement learning works. In particular he shows why two-person games of tactics and strategy fascinate scientists, programmers, and game enthusiasts and unite them in a common go

Machine learning with Go

📁 Machine learning with Go

✍ Whitenack, Daniel 📂 Library 📅 2017 🌐 English

Machine Learning With Go

📁 Machine Learning With Go

✍ Whitenack, Daniel 📂 Library 📅 2017 🏛 Packt Publishing 🌐 English

Machine Learning With Go

📁 Machine Learning With Go

✍ Daniel Whitenack 📂 Library 📅 2017 🏛 Packt Publishing 🌐 English

Machine Learning with Go

📁 Machine Learning with Go

✍ Daniel Whitenack 📂 Library 📅 2017 🏛 Packt 🌐 English

Machine Learning With Go

📁 Machine Learning With Go

✍ Daniel Whitenack 📂 Library 📅 2018 🏛 Packt 🌐 English