We introduce a method for constructing skills capable of solving tasks drawn from a
distribution of parameterized reinforcement learning problems. The method draws example …

We present a method for reinforcement learning of closely related skills that are
parameterized via a skill embedding space. We learn such skills by taking advantage of …

Many complex robot motor skills can be represented using elementary movements, and
there exist efficient techniques for learning parametrized motor plans using demonstrations …

We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in
continuous reinforcement learning domains. CST uses a changepoint detection method 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 …

Many control problems take place in continuous state-action spaces, eg, as in manipulator
robotics, where the control objective is often defined as finding a desired trajectory that …

Autonomous learning is one of the hallmarks of human and animal behavior, and
understanding the principles of learning will be crucial in order to achieve true autonomy in …

A fundamental challenge in reinforcement learning is to learn policies that generalize
beyond the operating domains experienced during training. In this paper, we approach this …

We demonstrate a sample-efficient method for constructing reusable parameterized skills
that can solve families of related motor tasks. Our method uses learned policies to analyze …

The acquisition and improvement of motor skills and control policies for robotics from trial
and error is of essential importance if robots should ever leave precisely pre-structured …