Search
Now showing items 1-3 of 3
Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
(ACM, 2017)
The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts learning and the resulting performance. We compare the impact ...
Fully Asynchronous SPH Simulation
(ACM, 2017)
We present a novel method for fully asynchronous time integration of particle-based fluids using smoothed particle hydrodynamics (SPH). With our approach, we allow a dedicated time step for each particle. Therefore, we are ...
Authoring Motion Cycles
(ACM, 2017)
Motion cycles play an important role in animation production and game development. However, creating motion cycles relies on general-purpose animation packages with complex interfaces that require expert training. Our work ...