Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
413346 | Robotics and Autonomous Systems | 2006 | 11 Pages |
Abstract
The paper presents an architecture that allows the reactive visual navigation via an unsupervised reinforcement learning. This objective is reached using QQ-learning and a hierarchical approach to the developed architecture. Using these techniques requires a deviation from the Partially Observable Markov Decision Processes (POMDP) and some innovations: heuristic techniques for generalizing the experience and for treating the partial observability; a technique for the speed adjournment of the QQ function; the definition of a special reinforcement policy adequate for learning a complex task without supervision. The result is a satisfactory learning of the navigation assignment in a simulated environment.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
A. Montesanto, G. Tascini, P. Puliti, P. Baldassarri,