A Survey on Reinforcement Learning Methods in Character Animation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Computer Graphics Forum Année : 2022

A Survey on Reinforcement Learning Methods in Character Animation

Résumé

Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on their observation of the environment, and receive appropriate rewards which define the objective. This experience is then used to progressively improve the policy controlling the agent's behavior, typically represented by a neural network. This trained module can then be reused for similar problems, which makes this approach promising for the animation of autonomous, yet reactive characters in simulators, video games or virtual reality environments. This paper surveys the modern Deep Reinforcement Learning methods and discusses their possible applications in Character Animation, from skeletal control of a single, physically-based character to navigation controllers for individual agents and virtual crowds. It also describes the practical side of training DRL systems, comparing the different frameworks available to build such agents.
Fichier principal
Vignette du fichier
RL_in_CA_Survey.pdf (2.6 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03600947 , version 1 (08-03-2022)

Identifiants

Citer

Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C. Karen Liu, Julien Pettré, et al.. A Survey on Reinforcement Learning Methods in Character Animation. Computer Graphics Forum, 2022, pp.1-27. ⟨10.1111/cgf.14504⟩. ⟨hal-03600947⟩
402 Consultations
807 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More