Calinon, S., Kormushev, P. and Caldwell, D. G. (2013)
Compliant skills acquisition and multi-optima policy search with EM-based reinforcement learning
Robotics and Autonomous Systems 61:4, 369-379.


The democratization of robotics technology and the development of new actuators progressively bring robots closer to humans. The applications that can now be envisaged drastically contrast with the requirements of industrial robots. In standard manufacturing settings, the criterions used to assess performance are usually related to the robot’s accuracy, repeatability, speed or stiffness. Learning a control policy to actuate such robots is characterized by the search of a single solution for the task, with a representation of the policy consisting of moving the robot through a set of points to follow a trajectory. With new environments such as homes and offices populated with humans, the reproduction performance is portrayed differently. These robots are expected to acquire rich motor skills that can be generalized to new situations, while behaving safely in the vicinity of users. Skills acquisition can no longer be guided by a single form of learning, and must instead combine different approaches to continuously create, adapt and refine policies. The family of search strategies based on expectation-maximization (EM) looks particularly promising to cope with these new requirements. The exploration can be performed directly in the policy parameters space, by refining the policy together with exploration parameters represented in the form of covariances. With this formulation, RL can be extended to a multi-optima search problem in which several policy alternatives can be considered. We present here two applications exploiting EM-based exploration strategies, by considering parameterized policies based on dynamical systems, and by using Gaussian mixture models for the search of multiple policy alternatives.

Bibtex reference

  author="Calinon, S. and Kormushev, P. and Caldwell, D. G.",
  title="Compliant skills acquisition and multi-optima policy search with EM-based reinforcement learning",
  journal="Robotics and Autonomous Systems",


The video shows a Barrett WAM 7 DOFs manipulator learning to flip pancakes by reinforcement learning. The motion is encoded in a mixture of basis force fields through an extension of Dynamic Movement Primitives (DMP) that represents the synergies across the different variables through stiffness matrices. An Inverse Dynamics controller with variable stiffness is used for reproduction.

The skill is first demonstrated via kinesthetic teaching, and then refined by Policy learning by Weighting Exploration with the Returns (PoWER) algorithm. After 50 trials, the robot learns that the first part of the task requires a stiff behavior to throw the pancake in the air, while the second part requires the hand to be compliant in order to catch the pancake without having it bounced off the pan.

Video credits: Dr Petar Kormushev, Dr Sylvain Calinon

Go back to the list of publications