Accelerating autonomous learning by using heuristic selection of actions

This paper investigates how to make improved action selection for online policy learning in robotic scenarios using reinforcement learning (RL) algorithms. Since finding control policies using any RL algorithm can be very time consuming, we propose to combine RL algorithms with heuristic functions for selecting promising actions during the learning process. With this aim, we investigate the use of heuristics for increasing the rate of convergence of RL algorithms and contribute with a new learning algorithm, Heuristically Accelerated Q-learning (HAQL), which incorporates heuristics for action selection to the Q-Learning algorithm. Experimental results on robot navigation show that the use of even very simple heuristic functions results in significant performance enhancement of the learning rate.     

Activities of Selenia Spazio

Summary Selenia Spazio was involved since its beginning, more than twenty years ago, in scientific space missions, like almost all space industries in the world. In fact the European space organizations were mainly devoted to the development of autonomous launchers and to scientific research in the nearby and in the far away space. First programs in which Selenia Spazio had a role, designing and manufacturing space electronic equipment, were scientific satellites and ELDO launchers, followed by COSB and other cosmic research missions. In all these years cosmic physics and related research programs continued to receive technological support and see full involvement by space industry. To speed up publication, the proofs were not sent to the authors and were supervised by the Scientific Committee.     

Ueber die Flächen mit constanter negativer Krümmung

Ohne Zusammenfassung     

Hammer's X-ray problem is well-posed

Summary In un precedente articolo [2]G. Mägerl ed il secondo autore hanno dimostrato la buona posizione del problema ricostruttivo di Hammer, imponendo che il corpo convesso da ricostruire fosse contenuto in un preassegnato insieme limitato. Si dimostra qui che tale limitazione può essere tolta.Ricerca finanziata con fondi MPI.