Search Algorithms for Stochastic Grid-World Maze Navigation – Bc. Pavol Zaťko
Bc. Pavol Zaťko
Master's thesis
Search Algorithms for Stochastic Grid-World Maze Navigation
Search Algorithms for Stochastic Grid-World Maze Navigation
Abstract:
Táto práca porovnáva schopnosť viacerých algoritmov vytvárať stratégie na prehľadávanie bludiska napriek tomu, že robot vykonávajúci akcie vybrané algoritmami sa môže dopúšťať chýb. Algoritmom bolo dovolené obmedzene dlho v bludisku trénovať, potom sa v ňom museli rýchlo dostať k čo najviac cieľom. Okrem iných algoritmov sa táto práca zameriava hlavne na Monte Carlo tree search a Q-learning a pokúša …moreAbstract:
This thesis compares the ability of multiple algorithms to create strategies for navigating a maze despite the errors of the robot executing the actions chosen by the algorithms. The algorithms were allowed to train in a maze for a limited amount of time, then they were expected to quickly reach as many goals in it as possible. Among other algorithms, this thesis focuses in particular on Monte Carlo …more
Language used: English
Date on which the thesis was submitted / produced: 18. 5. 2021
Identifier:
https://is.muni.cz/th/ehu2k/
Thesis defence
- Date of defence: 21. 6. 2021
- Supervisor: RNDr. Petr Novotný, Ph.D.
- Reader: doc. RNDr. Tomáš Brázdil, Ph.D.
Citation record
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Theoretical computer science / Algorithms and Computational Models
Theses on a related topic
-
Monte Carlo Tree Search in Deep Reinforcement Learning Algorithms
Richard Schwarz -
Monte Carlo Tree Search in Verification of Markov Decision Processes
Ondřej Slámečka -
Navigace bludištěm pomocí prohledávání stromu metodou Monte Carlo
Ján Petrák -
Monte Carlo vyhledávácí techniky v deskových hrách
Radomír ŠKRABAL -
Navigace v neznámém a pevně daném prostředí pomocí deep reinforcement learning algoritmu
Gabriela HRUBÁ