One of the most formidable issues of RL application to real robot tasks is how to find a suitable state space, and this has been much more serious since recent robots tends to hav...
We propose an O(n4) algorithm to build the modular decomposition tree of hypergraphs of dimension 3 and show how this algorithm can be generalized to compute in O(n3k−5) time th...
We introduce a new way to compute common intervals of K permutations based on a very simple and general notion of generators of common intervals. This formalism leads to simple an...
Anne Bergeron, Cedric Chauve, Fabien de Montgolfie...
Abstract- Decomposing a complex computational problem into sub-problems, which are computationally simpler to solve individually and which can be combined to produce a solution to ...
Vineet R. Khare, Xin Yao, Bernhard Sendhoff, Yaoch...
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...