Balancing of competitive two-player Game Levels with Reinforcement Learning
Authors:
- 21 August 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
The balancing process for game levels in a competitive two-player context involves a lot of manual work and testing, particularly in non-symmetrical game levels. In this paper, we propose an architecture for automated balancing of tile-based levels within the recently introduced PCGRL framework (procedural content generation via reinforcement learning).Our architecture is divided into three parts: (1) a level generator, (2) a balancing agent and, (3) a reward modeling simulation. By playing the level in a simulation repeatedly, the balancing agent is rewarded for modifying it towards the same win rates for all players. To this end, we introduce a novel family of swap-based representations to increase robustness towards playability. We show that this approach is capable to teach an agent how to alter a level for balancing better and faster than plain PCGRL. In addition, by analyzing the agent’s swapping behavior, we can draw conclusions about which tile types influence the balancing most. We test and show our results using the Neural MMO (NMMO) environment in a competitive two-player setting.Keywords
All Related Versions
Funding Information
- Volkswagen Foundation
This publication has 23 references indexed in Scilit:
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-playScience, 2018
- DOOM Level Generation Using Generative Adversarial Networks2018
- Using a Surrogate Model of Gameplay for Automated Level Design2018
- Strategic Features and Terrain Generation for Balanced Heroes of Might and Magic III Maps2018
- Procedural Content Generation via Machine Learning (PCGML)IEEE Transactions on Games, 2018
- Evolving maps for match balancing in first person shooters2014
- On balance and dynamism in procedural content generation with self-adaptive evolutionary algorithmsNatural Computing, 2014
- Controllable procedural map generation via multiobjective evolutionGenetic Programming and Evolvable Machines, 2013
- Search-Based Procedural Content Generation: A Taxonomy and SurveyIEEE Transactions on Computational Intelligence and AI in Games, 2011