goodcatan

Tries not to play bad catan.

A work in progress.

Current state: Literature Review

Authors: Ross Anderson (rosshamish),

---

Table of Contents

1. Literature Survey
   1. University of Alberta Research
   2. Machine Learning Techniques
      1. Recurrent Neural Networks
      2. Hidden Markov Models
      3. Reinforcement Learning
      4. Convolutional Neural Networks
   3. Game AI Theory
   4. Chess AI Theory
   5. Catan Software Implementations
   6. Catan Software AI Implementations
2. Thoughts, Intuitions
3. Collecting Data
4. Evaluation Critera
5. The Performance Task
6. Results

Literature Survey

University of Alberta Research

Heads-up Limit Hold'em Poker is Solved (Bowling et al, 2015)

Solving Imperfect Information Games Using Decomposition (Neil Burch et al, 2014)

Reinforcement Learning and Artificial Intelligence Group Annual Reports (RLAI)

Machine Learning Techniques

Recurrent Neural Networks

The Unreasonable Effectiveness of Recurrent Neural Networks (Karpathy, 2015)
Some notes about this paper.

Monte-Carlo Methods

Monte-Carlo Tree Search: A New Framework for Game AI (Chaslot et al, 2008)
Some notes about this paper.

Hidden Markov Models

A Tutorial on Hidden Markov Models and Selected Application in Speech Recognition (Rabiner, 1989)
Some notes about this paper.

Reinforcement Learning

Reinforcement Learning of Strategies for Settlers of Catan (Pfeiffer, 2004)
Some notes about this paper.

Strategic Dialogue Management via Deep Reinforcement Learning (Cuayahuitl, 2015 (b))

Convolutional Neural Networks

Game AI Theory

An Introduction to General Game Learning (Fisher, 2014)
Some notes about this paper

Learning Trading Negotiations Using Manually and Automatically Labelled Data ([Cuayáhuitl])
Cuayáhuitl, Heriberto, Simon Keizer, and Oliver Lemon. "Learning Trading Negotiations Using Manually and Automatically Labelled Data." International Conference on Tools with Artificial Intelligence (ICTAI). 2015.

Strategic Dialogue Management via Deep Reinforcement Learning (Cuayahuitl, 2015 (b))

Chess AI Theory

Giraffe: Using Deep Reinforcement Learning to Play Chess (Lai, 2015)
Some notes about this paper.

A Brief Survey of Chess AI: Strategy and Implementation (Montoya, 2012)
Some notes about this paper.

Programming a Computer for Playing Chess (Shannon, 1949)

A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence (McCarthy et al, 1955)

An Analysis of Alpha-Beta Pruning (Knuth & Moore, 1975)

Catan Software Implementations

JSettlers2

• Author(s): Jeremy Monin
• License: GPLv3
• Features: network support, bot support
• Notes:

Pioneers

• Author(s): Many maintainers, see the project page
• License: GPLv2
• Features:
• Notes: Last update 11-2014. Hosted on sourceforge.

Settlers3D

• Author(s):
• License:
• Features: 3D GUI
• Notes: Hosted on sourceforge.

Catan Software AI Implementations

JSettlers2

• Author(s): Jeremy Monin
• License: GPLv3