BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035306Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_144@linklings.com
SUMMARY:Control VAE: Model-Based Learning of Generative Controllers for Ph
 ysics-Based Characters
DESCRIPTION:Technical Papers\n\nControl VAE: Model-Based Learning of Gener
 ative Controllers for Physics-Based Characters\n\nYao, Song, Chen, Liu\n\n
 In this paper, we introduce Control VAE, a novel model-based framework for
  learning generative motion control policies based on variational autoenco
 ders (VAE). Our framework can learn a rich and flexible latent representat
 ion of skills and a skill-conditioned generative control policy from a div
 erse set of unorganized motion sequences, which enables the generation of 
 realistic human behaviors by sampling in the latent space and allows high-
 level control policies to reuse the learned skills to accomplish a variety
  of downstream tasks. In the training of Control VAE, we employ a learnabl
 e world model to realize direct supervision of the latent space and the co
 ntrol policy. This world model effectively captures the unknown dynamics o
 f the simulation system, enabling efficient model-based learning of high-l
 evel downstream tasks. We also learn a state-conditional prior distributio
 n in the VAE-based generative control policy, which generates a skill embe
 dding that outperforms the non-conditional priors in downstream tasks. We 
 demonstrate the effectiveness of Control VAE using a diverse set of tasks,
  which allows realistic and interactive control of the simulated character
 s.\n\nRegistration Category: FULL ACCESS, EXPERIENCE PLUS ACCESS, EXPERIEN
 CE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH\n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_144&sess=sess15
 3
END:VEVENT
END:VCALENDAR