We present a reformulation of the stochastic optimal control problem in terms of KL
divergence minimisation, not only providing a unifying perspective of previous approaches …

In this work, we propose a novel formulation of planning which views it as a probabilistic
inference problem over future optimal trajectories. This enables us to use sampling methods …

We present an approach for asymptotically optimal motion planning for kinodynamic
systems with arbitrary nonlinear dynamics amid obstacles. Optimal sampling-based …

Functional gradient algorithms (eg CHOMP) have recently shown great promise for
producing locally optimal motion for complex many degree-of-freedom robots. A key …

Reinforcement learning methods are being applied to control problems in robotics domain.
These algorithms are well suited for dealing with the continuous large scale state spaces in …

Motion can be described in several alternative representations, including joint configuration
or end-effector spaces, but also more complex topology-based representations that imply a …

While reinforcement learning algorithms provide automated acquisition of optimal policies,
practical application of such methods requires a number of design decisions, such as …

We present Extended LQR, a novel approach for locally-optimal control for robots with non-
linear dynamics and non-quadratic cost functions. Our formulation is conceptually different …

Until now, design of variable physical impedance actuators (VIAs) has been limited mainly to
realising variable stiffness while other components of impedance shaping, such as damping …

In this work we show how to represent policies as programs: that is, as stochastic simulators
with tunable parameters. To learn the parameters of such policies we develop connections …