Reinforcement learning in videogames
Year: 2017
Type: dissertation
Abstract: While there are still a lot of projects and papers focused on: given a game, discover and measure which\nis the best algorithm for it, I decided to twist things around and decided to focus on two algorithms and\nits parameters be able to tell which games will be best approachable with it.\nTo do this, I will be implementing both algorithms Q-Learning and SARSA, helping myself with Neural\nNetworks to be able to represent the vast state space that the games have. The idea is to implement the\nalgorithms as general as possible.This way in case someone wanted to use my algorithms for their game,\nit would take the less amount of time possible to adapt the game for the algorithm.\nI will be using some games that are used to make Artificial Intelligence competitions so I have\na base to work with, having more time to focus on the actual algorithm implementation and results\ncomparison.
Author: Alex Osés Laza
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2777031522