Technical Paper
:
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
TimeThursday, 16 August 201811:07am - 11:29am
LocationWest Building, Room 109-110, Vancouver Convention Centre
DescriptionWe present a deep reinforcement learning framework that enables simulated characters to imitate a rich repertoire of highly dynamic and acrobatic skills from reference motion clips.
Authors
Xue Bin Peng
University of California, Berkeley
Pieter Abbeel
University of California, Berkeley
Sergey Levine
University of California, Berkeley
Michiel van de Panne
University of British Columbia
Session Chair
Doug James
Stanford University
Pixar Animation Studios
Authors
Xue Bin Peng
Pieter Abbeel
Sergey Levine
Michiel van de Panne
Event Type
Technical Paper
Registration Levels
F
FP
Personas
R&E