Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 350 | DOWNLOAD 56

Application of DeepLearning Algorithm on Minecraft

Download
Van de Goor, Elodie ULiège
Promotor(s) : Ernst, Damien ULiège
Date of defense : 8-Sep-2016/9-Sep-2016 • Permalink : http://hdl.handle.net/2268.2/1686
Details
Title : Application of DeepLearning Algorithm on Minecraft
Translated title : [fr] Application d'une méthode d'apprentissage profond dans Minecraft
Author : Van de Goor, Elodie ULiège
Date of defense  : 8-Sep-2016/9-Sep-2016
Advisor(s) : Ernst, Damien ULiège
Committee's member(s) : Geurts, Pierre ULiège
Wehenkel, Louis ULiège
Gemine, Quentin ULiège
François-Lavet, Vincent ULiège
Language : English
Number of pages : 73
Keywords : [en] deep learning
[en] Machine learning
[en] Minecraft
[en] Deer
[en] DeepMind
[en] deep Q-network
[en] reinforcement learning
Discipline(s) : Engineering, computing & technology > Computer science
Target public : Researchers
Professionals of domain
Student
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master en ingénieur civil en informatique, à finalité approfondie
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] Some years ago, Google DeepMind released a paper describing an agent architecture, DQN. This agent was able to learn to play better than humans in 49 different Atari game while receiving only the game screen and scores as inputs. With these kinds of results we can ask ourselves how well this agent could do in the environment of a new game. The purpose of this thesis is to make the DeepMind agent evolve into Minecraft and make it easily adaptable to many kinds of tasks. Its task is to destroy as many mobs as possible in a room.
The implementation of a DeepMind agent has been carried out in the game Minecraft through the ULg program Deer. The communication between Deer and minecraft was designed in a modular way so it can be adapted to other tasks or even other games. A number of experiments have been conducted to test different combination of parameters.
The learning speed of the agent was impressive when we consider the small learning phase it has comparing to the Atari learning phases. It made good results and when we increase the number of step to 80,000 it was as good as a human player, even developing strategies to find and trap the mobs. However it still has a stability problem.

These results are encouraging and more tests should help to reach an even better score. Once this is done, the difficulty of the task can be increased to a moving agent for example. Step by step, it is possible to test more and more complex tasks by making the agent evolve with other paper results or other machine learning mechanisms. This environment will allow making both the agents architecture and the tasks evolve to whatever one would want.


File(s)

Document(s)

File
Access Application of a Deep Learning algorithm on Minecraft.pdf
Description:
Size: 9.42 MB
Format: Adobe PDF

Annexe(s)

File
Access run_minecraft.py
Description:
Size: 4.27 kB
Format: Unknown
File
Access minecraft_env.py
Description:
Size: 7.28 kB
Format: Unknown
File
Access Summary.pdf
Description:
Size: 306.68 kB
Format: Adobe PDF

Author

  • Van de Goor, Elodie ULiège Université de Liège > Master ingé. civ. info., fin. appr. (ex 2e master)

Promotor(s)

Committee's member(s)

  • Geurts, Pierre ULiège Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
    ORBi View his publications on ORBi
  • Wehenkel, Louis ULiège Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
    ORBi View his publications on ORBi
  • Gemine, Quentin ULiège Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids
    ORBi View his publications on ORBi
  • François-Lavet, Vincent ULiège Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore)
    ORBi View his publications on ORBi
  • Total number of views 350
  • Total number of downloads 56










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.