Zpět na vyhledávání

Tomáš Kancko

Bachelor's thesis

Reinforcement Learning for the Game of Battleship

Reinforcement Learning for the Game of Battleship
Abstract:
Bakalárska práca rozoberá využiteľnosť heuristík a vyhľadávacích algoritmov na hre Battleship. Prvá časť obsahuje všeobecný prehľad o hre. Druhá časť sa skladá z analýzy a implementácie rôznych heuristík a porovnáva ich. Tretia časť rozoberá MCTS a jeho parametre, formuláciu (PO)MDP modelu. V poslednej časti sa nachádza vyhodnotenie a porovnanie všetkých metód.
Abstract:
The thesis explores the usability of general heuristic search algorithms in the Battleship domain. The first part of the thesis is an overview of the Battleship game. The second part analyses different designs, patterns and implementations of several heuristics and compares them. The third part is an overview of the MCTS algorithm and its parameters. The thesis also contains an outline of the formulation …more
 

Keywords

Battleship Monte Carlo tree search Markov decision process heuristics neural network NEAT
 
Language used: English
Date on which the thesis was submitted / produced: 20. 7. 2020
Identifier: https://is.muni.cz/th/oupp1/

Thesis defence

  • Date of defence: 25. 9. 2020
  • Supervisor: RNDr. Petr Novotný, Ph.D.
  • Reader: Mgr. Jiří Vahala

Citation record

Cite this text

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 informatiky
Složka Reference to the local database directory of the institution