Imitation learning techniques aim to mimic human behavior in a given task. An agent (a
learning machine) is trained to perform a task from demonstrations by learning a map** …

As robots and other intelligent agents move from simple environments and problems to more
complex, unstructured settings, manually programming their behavior has become …

Reinforcement learning offers to robotics a framework and set of tools for the design of
sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic …

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 …

Biological systems, including human beings, have the innate ability to perform complex
tasks in a versatile and agile manner. Researchers in sensorimotor control have aimed to …

Many motor skills in humanoid robotics can be learned using parametrized motor primitives
as done in imitation learning. However, most interesting motor learning problems are high …

Learning new motor tasks from physical interactions is an important goal for both robotics
and machine learning. However, when moving beyond basic skills, most monolithic machine …

Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot
learning. To be effective, action learning should not be limited to direct replication of …

One promising approach for robots efficiently learning skills is to learn manipulation skills
from human tutors by demonstration and then generalize these learned skills to complete …

Batch reinforcement learning methods provide a powerful framework for learning efficiently
and effectively in autonomous robots. The paper reviews some recent work of the authors …