Dataset: Q-learning Q-tables for 'A drone simulator with smart objectives, developed using artificial intelligence technologies to implement user stories'

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: Martyniuk Maksym, Vakaliuk Tetiana
DOI: 10.5281/zenodo.18208953
Cited by: 0

Abstract

This dataset contains tabular Q-learning Q-tables produced in an Unreal Engine 5 drone simulator with intelligent adaptive targets. The data represent state-action values (Q-values) for three high-level actions (TowardGoal, TowardCover, RandomMove) across discretised environment sections (sectionKey). Files included: RLData.json, initial (pre-training) Q-table used to initialise the agent policy. RLDataTrained.json, Q-table after 20 training episodes, reflecting learned behaviour.

Fields of Study & Subjects

Reinforcement Learning in Robotics Artificial Intelligence in Games Educational Games and Gamification

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
10 January 2026
Language
EN
Document type
Dataset