Applying Hindsight Experience Replay to Procedural Level Generation

Evan Kusuma Susanto, Handayani Tjandrasa

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Designing a video game level requires a precise balance in difficulty adjustment as a level that is too simple will cause players to lose interest quickly. On the other hand, making a level too complicated will frustrate the players, making them abandon the game. We propose a new method to make a level generator that can learn how to design a game level by itself. Our proposed method can be used for different games with only minimal adjustments. We improve the previously proposed method by making our generator able to design a level that satisfies every user's criterion. We do this by combining Procedural Content Generation via Reinforcement Learning with the Hindsight Experience Replay method. We use our model to generate levels from 4 different games and compare the success rate with a random agent. Our model achieves more than 90% success rate for almost every scenario and performs much better when compared to a random agent.

Original languageEnglish
Title of host publication3rd 2021 East Indonesia Conference on Computer and Information Technology, EIConCIT 2021
EditorsRayner Alfred, Haviluddin Haviluddin, Aji Prasetya Wibawa, Joan Santoso, Fachrul Kurniawan, Hartarto Junaedi, Purnawansyah Purnawansyah, Endang Setyati, Herman Thuan To Saurik, Esther Irawati Setiawan, Eka Rahayu Setyaningsih, Edwin Pramana, Yosi Kristian, Kelvin Kelvin, Devi Dwi Purwanto, Eunike Kardinata, Prananda Anugrah
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages427-432
Number of pages6
ISBN (Electronic)9781665405140
DOIs
Publication statusPublished - 9 Apr 2021
Event3rd East Indonesia Conference on Computer and Information Technology, EIConCIT 2021 - Virtual, Surabaya, Indonesia
Duration: 9 Apr 202111 Apr 2021

Publication series

Name3rd 2021 East Indonesia Conference on Computer and Information Technology, EIConCIT 2021

Conference

Conference3rd East Indonesia Conference on Computer and Information Technology, EIConCIT 2021
Country/TerritoryIndonesia
CityVirtual, Surabaya
Period9/04/2111/04/21

Keywords

  • Deep Reinforcement Learning
  • Multi-Goal Reinforcement Learning
  • Procedural Level Generation

Fingerprint

Dive into the research topics of 'Applying Hindsight Experience Replay to Procedural Level Generation'. Together they form a unique fingerprint.

Cite this