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:20231212T141000
DTEND;TZID=Australia/Melbourne:20231212T142500
UID:siggraphasia_SIGGRAPH Asia 2023_sess120_papers_543@linklings.com
SUMMARY:AdaptNet: Policy Adaptation for Physics-Based Character Control
DESCRIPTION:Technical Papers\n\nPei Xu (Clemson University, Roblox); Kaixi
 ang Xie (McGill University); Sheldon Andrews (École de technologie supérie
 ure, Roblox); Paul G. Kry (McGill University); Michael Neff (University of
  California Davis); Morgan McGuire (Roblox, University of Waterloo); Ioann
 is Karamouzas (University of California Riverside); and Victor Zordan (Rob
 lox, Clemson University)\n\nMotivated by human’s ability to adapt skills i
 n the learning of new ones, this paper presents AdaptNet, an approach for 
 modifying the latent space of existing policies to allow new behaviors to 
 be quickly learned from like tasks in comparison to learning from scratch.
  Building on top of a given reinforcement learning controller, AdaptNet us
 es a two-tier hierarchy that augments the original state embedding to supp
 ort modest changes in a behavior and further modifies the policy network l
 ayers to make more substantive changes. The technique is shown to be effec
 tive for adapting existing physics-based controllers to a wide range of ne
 w styles for locomotion, new task targets, changes in character morphology
 , and extensive changes in environment. Furthermore, it exhibits significa
 nt increase in learning efficiency, as indicated by greatly reduced traini
 ng times when compared to training from scratch or using other approaches 
 that modify existing policies.\n\nRegistration Category: Full Access\n\nSe
 ssion Chair: Jungdam Won (Seoul National University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_543&sess=sess120
END:VEVENT
END:VCALENDAR