We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
Pedro Alejandro Ortega, Daniel Alexander Braun, Si...
Abstract. CAT(0) metric spaces constitute a far-reaching common generalization of Euclidean and hyperbolic spaces and simple polygons: any two points x and y of a CAT(0) metric spa...
Reactive planning using assumptions is a well-known approach to tackle complex planning problems for nondeterministic, partially observable domains. However, assumptions may be wr...
We consider a generalization of the PDB homomorphism abstractions to what is called "structural patterns". The bais in abstracting the problem in hand into provably trac...
We give a surprisingly short proof that in any planar arrangement of Ò curves where each pair intersects at most a fixed number (×) of times, the -level has subquadratic (Ç´...