Humans are able to perform a myriad of sophisticated tasks by drawing upon skills acquired
through prior experience. For autonomous agents to have this capability, they must be able …

Using joint actuators to drive the skeletal movements is a common practice in character
animation, but the resultant torque patterns are often unnatural or infeasible for real humans …

Autonomous agents situated in real-world environments must be able to master large
repertoires of skills. While a single short skill can be learned quickly, it would be impractical …

Autonomous agents situated in real-world environments must be able to master large
repertoires of skills. While a single short skill can be learned quickly, it would be impractical …

This thesis studies the broad problem of learning robust control policies for difficult physics-
based motion control tasks such as locomotion and navigation. A number of avenues are …

In common real-world robotic operations, action and state spaces can be vast and
sometimes unknown, and observations are often relatively sparse. How do we learn the full …

Cette thèse traite de l'animation de personnages virtuels composés de corps rigides reliés
par des articulations et contrôlés par des interactions physiques (forces et moments). Le …