MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters

Simple item page
dc.contributor.authorYounes, Mohameden_US
dc.contributor.authorKijak, Ewaen_US
dc.contributor.authorKulpa, Richarden_US
dc.contributor.authorMalinowski, Simonen_US
dc.contributor.authorMulton, Francken_US
dc.contributor.editorWang, Huaminen_US
dc.contributor.editorYe, Yutingen_US
dc.contributor.editorVictor Zordanen_US
dc.date.accessioned2023-10-16T12:32:52Z
dc.date.available2023-10-16T12:32:52Z
dc.date.issued2023
dc.description.abstractSimulating realistic interaction and motions for physics-based characters is of great interest for interactive applications, and automatic secondary character animation in the movie and video game industries. Recent works in reinforcement learning have proposed impressive results for single character simulation, especially the ones that use imitation learning based techniques. However, imitating multiple characters interactions and motions requires to also model their interactions. In this paper, we propose a novel Multi-Agent Generative Adversarial Imitation Learning based approach that generalizes the idea of motion imitation for one character to deal with both the interaction and the motions of the multiple physics-based characters. Two unstructured datasets are given as inputs: 1) a single-actor dataset containing motions of a single actor performing a set of motions linked to a specific application, and 2) an interaction dataset containing a few examples of interactions between multiple actors. Based on these datasets, our system trains control policies allowing each character to imitate the interactive skills associated with each actor, while preserving the intrinsic style. This approach has been tested on two different fighting styles, boxing and full-body martial art, to demonstrate the ability of the method to imitate different styles.en_US
dc.description.number3
dc.description.sectionheadersPhysics-based Character Control
dc.description.seriesinformationProceedings of the ACM on Computer Graphics and Interactive Techniques
dc.description.volume6
dc.identifier.doi10.1145/3606926
dc.identifier.issn2577-6193
dc.identifier.urihttps://doi.org/10.1145/3606926
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1145/3606926
dc.publisherACM Association for Computing Machineryen_US
dc.subjectCCS Concepts: Computing methodologies -> Procedural animation; Adversarial learning; Multiagent reinforcement learning Character Animation, Multi-Agent Reinforcement Learning, Adversarial Imitation learning, Physics-based Simulation, Motion Capture"
dc.subjectComputing methodologies
dc.subjectProcedural animation
dc.subjectAdversarial learning
dc.subjectMultiagent reinforcement learning Character Animation
dc.subjectMulti
dc.subjectAgent Reinforcement Learning
dc.subjectAdversarial Imitation learning
dc.subjectPhysics
dc.subjectbased Simulation
dc.subjectMotion Capture"
dc.titleMAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based charactersen_US
Files
Collections
SCA 2023: Eurographics/SIGGRAPH Symposium on Computer Animation