Generalized circle agent for geometry friends using deep reinforcement learning

Azmi Can Özgen, Mandana Fasounaki, Hazim Kemal Ekenel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Reinforcement learning began to perform at human-level success in game intelligence after deep learning revolution. Geometry Friends is a puzzle game, where we can benefit from deep learning and expect to have successful game playing agents. In the game, agents are collecting targets in two dimensional environment and they try to overcome obstacles in the way. In this paper, Q-learning approach is applied to this game and a generalized circle agent for different types of environment is implemented. Agent is trained by giving only screen pixels as input via a Convolutional Neural Network. Experimental results show that with the proposed method game completion rate and completion times are improved compared to random agent.

Original languageEnglish (US)
Title of host publication26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538615010
DOIs
StatePublished - Jul 5 2018
Event26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 - Izmir, Turkey
Duration: May 2 2018May 5 2018

Publication series

Name26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

Conference

Conference26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
Country/TerritoryTurkey
CityIzmir
Period5/2/185/5/18

Keywords

  • Convolutional Neural Networks
  • Game-playing AI
  • Q-learning
  • Reinforcement Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing

Fingerprint

Dive into the research topics of 'Generalized circle agent for geometry friends using deep reinforcement learning'. Together they form a unique fingerprint.

Cite this