Institutional Repository of Vilnius University
Deep Q-Learning pritaikymas judančio veikėjo sekimui 2D gaudynių žaidime naudojant vidinį LiDAR žemėlapį /
Abstract
dc:descriptionIn this thesis the Rainbow DeepQ Network (DQN) algorithm is tested in a custommade 2D platformer tag game with three different state representations: Full Screenshot, LiDAR map with persistent player state knowledge (oracle) and LiDAR map with a line of sight restriction. The algo rithm is applied to both the seeker and runner agents creating a multiagent environment. It covers the environment creation, Rainbow DQN details and tests comparing the state representations.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Švarlys, Matas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308338512&prefLang=en_US