Configurable Agent With Reward As Input: A Play-Style Continuum Generation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Configurable Agent With Reward As Input: A Play-Style Continuum Generation

Rémi Labory
  • Fonction : Auteur
  • PersonId : 1220058
Vincent Corruble

Résumé

Modern video games are becoming richer and more complex in terms of game mechanics. This complexity allows for the emergence of a wide variety of ways to play the game across the players. From the point of view of the game designer, this means that one needs to anticipate a lot of different ways the game could be played. Machine Learning (ML) could help address this issue. More precisely, Reinforcement Learning is a promising answer to the need of automating video game testing. In this paper we present a video game environment which lets us define multiple play-styles. We then introduce CARI: a Configurable Agent with Reward as Input. An agent able to simulate a wide continuum range of play-styles. It is not constrained to extreme archetypal behaviors like current methods using reward shaping. In addition it achieves this through a single training loop, instead of the usual one loop per playstyle. We compare this novel training approach with the more classic reward shaping approach and conclude that CARI can also outperform the baseline on archetypes generation. This novel agent could be used to investigate behaviors and balancing during the production of a video game with a realistic amount of training time.
Fichier principal
Vignette du fichier
2211.16221.pdf (859.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03957644 , version 1 (26-01-2023)

Identifiants

Citer

Pierre Le Pelletier de Woillemont, Rémi Labory, Vincent Corruble. Configurable Agent With Reward As Input: A Play-Style Continuum Generation. 2021 IEEE Conference on Games (CoG), IEEE, Aug 2021, Copenhagen (Virtual), Denmark. pp.1-8, ⟨10.1109/CoG52621.2021.9619127⟩. ⟨hal-03957644⟩
14 Consultations
19 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More