Change search
ReferencesLink to record
Permanent link

Direct link
Deep reinforcement learning compared with Q-table learning applied to backgammon
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2016 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
En jämförelse mellan deep reinforcement learning och Q-tabeller i spelet backgammon (Swedish)
Abstract [en]

Reinforcement learning attempts to mimic how humans react to their surrounding environment by giving feedback to software agents based on the actions they take. To test the capabilities of these agents, researches have long regarded board games as a powerful tool. This thesis compares two approaches to reinforcement learning in the board game backgammon, a Q-table and a deep reinforcement network. It was determined which approach surpassed the other in terms of accuracy and convergence rate towards the perceived optimal strategy. The evaluation is performed by training the agents using the self-learning approach. After variable amounts of training sessions, the agents are benchmarked against each other and a third, random agent. The results derived from the study indicate that the convergence rate of the deep learning agent is far superior to that of the Q-table agent. However, the results also indicate that the accuracy of Q-tables is greater than that of deep learning once the former has mapped the environment.

Place, publisher, year, edition, pages
2016. , 30 p.
National Category
Computer Science
URN: urn:nbn:se:kth:diva-186545OAI: diva2:927740
Available from: 2016-05-18 Created: 2016-05-13 Last updated: 2016-05-18Bibliographically approved

Open Access in DiVA

PFinnmanMWinberg_dkand16(3145 kB)113 downloads
File information
File name FULLTEXT01.pdfFile size 3145 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 113 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 548 hits
ReferencesLink to record
Permanent link

Direct link