Learning Control Systems-Review and Outlook
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special memorial issue for Professor King-Sun Fu
Grammatical Inference: Introduction and Survey-Part II
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special memorial issue for Professor King-Sun Fu
Learning automata: an introduction
Learning automata: an introduction
Introduction to the theory of neural computation
Introduction to the theory of neural computation
First results with Dyna, an integrated architecture for learning, planning and reacting
Neural networks for control
Intelligent robotic systems: theory, design and applications
Intelligent robotic systems: theory, design and applications
Technical Note: \cal Q-Learning
Machine Learning
An introduction to intelligent and autonomous control
An introduction to intelligent and autonomous control
Techniques for selecting pose algorithms
Automatica (Journal of IFAC)
Some studies in machine learning using the game of checkers
Computers & thought
Design of Intelligent Control Systems Based on Hierarchical Stochastic Automata
Design of Intelligent Control Systems Based on Hierarchical Stochastic Automata
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Hi-index | 0.00 |
Learning is a research topic often pursued by researchers in Robotics, as results in this area may significantly reduce the time required to teach complex tasks to a robot. This paper introduces an approach to the reinforcement learning of robotic tasks. Besides leading to learning algorithms with no special complexity, reinforcement learning schemes require underlying performance measures applicable to a wide category of algorithms usually implemented in robotic systems. One such measure, balancing the reliability and computational cost of an algorithm, is introduced here. The measure is applied to learn the best among a set of alternative tasks capable of executing a command communicated to an intelligent machine. Furthermore, the measure definition reduces the significance of the learning scheme slow convergence. We assume that the alternative tasks are pre-defined by an expert, thus enhancing the fact that a priori knowledge of the steps composing a robotic task is often relevant, even though other learning approaches minimize its use.