Most policy search (PS) algorithms require thousands of training episodes to find an
effective policy, which is often infeasible with a physical robot. This survey article focuses on …

Policy search is a subfield in reinforcement learning which focuses on finding good
parameters for a given policy parametrization. It is well suited for robotics as it can cope with …

The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on
uncertain dynamical models: after each episode, they first learn a dynamical model of the …

In robotics, lower-level controllers are typically used to make the robot solve a specific task
in a fixed context. For example, the lower-level controller can encode a hitting movement …

Exploration-based reinforcement learning on real robot systems is generally time-intensive
and can lead to catastrophic robot failures. Therefore, simulation-based policy search …

In robotics, controllers make the robot solve a task within a specific context. The context can
describe the objectives of the robot or physical properties of the environment and is always …

A common belief in model-free reinforcement learning is that methods based on random
search in the parameter space of policies exhibit significantly worse sample complexity than …

Autonomous learning has been a promising direction in control and robotics for more than a
decade since data-driven learning allows to reduce the amount of engineering knowledge …

Policy improvement methods seek to optimize the parameters of a policy with respect to a
utility function. Owing to current trends involving searching in parameter space (rather than …

Reinforcement learning (RL) can be a tool for designing policies and controllers for robotic
systems. However, the cost of real-world samples remains prohibitive as many RL …