K Hausman, JT Springenberg, Z Wang… - International …, 2018 - openreview.net
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 …
J Kober, J Peters - Advances in neural information …, 2008 - proceedings.neurips.cc
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 Sonar, V Pacelli, A Majumdar - Learning for Dynamics …, 2021 - proceedings.mlr.press
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 …
J Peters, S Schaal - 2006 IEEE/RSJ international conference …, 2006 - ieeexplore.ieee.org
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 …