We combine three threads of research on approximate dynamic programming: sparse random sampling of states, value function and policy approximation using local models, and using lo...
The trend towards autonomic systems emphasizes the need for implementation frameworks for autonomic features. In this paper we describe a general framework for the development of ...
- In this paper the design and kinematic performances are presented for a low-cost parallel manipulator with 4 driven cables. It has been conceived for an easy programming of its o...
Erika Ottaviano, Marco Ceccarelli, Alessio Paone, ...
We consider the policy search approach to reinforcement learning. We show that if a “baseline distribution” is given (indicating roughly how often we expect a good policy to v...
J. Andrew Bagnell, Sham Kakade, Andrew Y. Ng, Jeff...
Pipeline, Delta, and Black Hole are three simple patterns used in concurrent software design. We recently presented these and other patterns for parallelism at a nine-hour worksho...
Matthew C. Jadud, Jon Simpson, Christian L. Jacobs...