A Survey on Reinforcement Learning Methods in Character Animation

Simple item page
dc.contributor.authorKwiatkowski, Arielen_US
dc.contributor.authorAlvarado, Eduardoen_US
dc.contributor.authorKalogeiton, Vickyen_US
dc.contributor.authorLiu, C. Karenen_US
dc.contributor.authorPettré, Julienen_US
dc.contributor.authorPanne, Michiel van deen_US
dc.contributor.authorCani, Marie-Pauleen_US
dc.contributor.editorMeneveaux, Danielen_US
dc.contributor.editorPatanè, Giuseppeen_US
dc.date.accessioned2022-04-22T07:00:32Z
dc.date.available2022-04-22T07:00:32Z
dc.date.issued2022
dc.description.abstractReinforcement 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.en_US
dc.description.documenttypestar
dc.description.number2
dc.description.sectionheadersState of the Art Reports
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14504
dc.identifier.issn1467-8659
dc.identifier.pages613-639
dc.identifier.pages27 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14504
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14504
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies --> Reinforcement learning; Animation
dc.subjectComputing methodologies
dc.subjectReinforcement learning
dc.subjectAnimation
dc.titleA Survey on Reinforcement Learning Methods in Character Animationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i2pp613-639.pdf
Size:
2.7 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2022 - STARs (CGF 41-2)