BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070242Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T140000
DTEND;TZID=Australia/Melbourne:20231212T141000
UID:siggraphasia_SIGGRAPH Asia 2023_sess120_papers_619@linklings.com
SUMMARY:C·ASE: Learning Conditional Adversarial Skill Embeddings for Physi
 cs-based Characters
DESCRIPTION:Technical Papers\n\nZhiyang Dou (The University of Hong Kong (
 HKU)), Xuelin Chen and Qingnan Fan (Tencent AI Lab), Taku Komura (Universi
 ty of Hong Kong), and Wenping Wang (Texas A&M University)\n\nWe present C·
 ASE, an efficient and effective framework that learns conditional Adversar
 ial Skill Embeddings for physics-based characters. Our physically simulate
 d character can learn a diverse repertoire of skills while providing contr
 ollability in the form of direct manipulation of the skills to be performe
 d. C·ASE divides the heterogeneous skill motions into distinct subsets con
 taining homogeneous samples for training a low-level conditional model to 
 learn conditional behavior distribution. The skill-conditioned imitation l
 earning naturally offers explicit control over the character's skills afte
 r training. The training course incorporates the focal skill sampling, ske
 letal residual forces, and element-wise feature masking to balance diverse
  skills of varying complexities, mitigate dynamics mismatch to master agil
 e motions and capture more general behavior characteristics, respectively.
  Once trained, the conditional model can produce highly diverse and realis
 tic skills, outperforming state-of-the-art models, and can be repurposed i
 n various downstream tasks. In particular, the explicit skill control hand
 le allows a high-level policy or user to direct the character with desired
  skill specifications, which we demonstrate is advantageous for interactiv
 e character animation.\n\nRegistration Category: Full Access\n\nSession Ch
 air: Jungdam Won (Seoul National University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_619&sess=sess120
END:VEVENT
END:VCALENDAR