The self-refinement approach is thus used to refine this initial estimate, by using as policy parameters the centers of the GMM, as well as the first eigencomponents of ordered eigendecompositions of the covariances (directions of the main axes of the ellipsoids).
One option for implementing such self-refinement is to use an EM-based stochastic optimization algorithm to refine the GMM parameters encoding the movement, similarly as in [18].
Said Mr. Theodore: "Where they're from and where I'm from, self-refinement isn't welcome in a sense.
The Communist Party is coming to join scholars in the view that Confucian principles of achieving harmony through self-refinement in manners and taste could help to achieve the "harmonious society", the cornerstone of Mr Hu's own thinking.
(b) Reproduction on the robot after self-refinement.
The approach is tested in simulation by imitation and self-refinement of an octopus reaching motion.
(a-f) A sample search in the augmented goal-policy space ζ is plotted for six selected self-refinement iterations.
Dayan and Hinton originally suggested that a self-refinement problem can be tackled by EM to avoid gradient computation [33].
Figure 11 Qualitative comparison of the octopus and STIFF-FLOP robot movements, before and after self-refinement.
The model parameters above can then be optimized through a self-refinement algorithm with an objective or reward function defined according to the different objectives of the task.
In some situations, the design of efficient self-refinement algorithms is crucial for the robot to learn how to perform a task in new situations [16].
