Physics simulation offers the possibility of truly responsive and realistic animation. Despite
wide adoption of physics simulation for the animation of passive phenomena, such as fluids …

Learning physics-based locomotion skills is a difficult problem, leading to solutions that
typically exploit prior knowledge of various forms. In this paper we aim to learn a variety of …

Reinforcement learning offers a promising methodology for developing skills for simulated
characters, but typically requires working with sparse hand-crafted features. Building on …

We present a real-time character control mechanism using a novel neural network
architecture called a Phase-Functioned Neural Network. In this network structure, the …

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 …

Humans are highly adept at walking in environments with foot placement constraints,
including stepping‐stone scenarios where footstep locations are fully constrained. Finding …

In this work, we present MoConVQ, a novel unified framework for physics-based motion
control leveraging scalable discrete representations. Building upon vector quantized …

We present a control strategy for physically-simulated walking motions that generalizes well
across gait parameters, motion styles, character proportions, and a variety of skills. The …

We propose a novel representation of motion data and control that enables characters with
both highly agile responses to user input and natural handling of arbitrary external …

We present a dynamic controller to physically simulate under-actuated three-dimensional
full-body biped locomotion. Our data-driven controller takes motion capture reference data to …