Reinforcement Learning and its Relationship to Supervised Learning
نویسندگان
چکیده
The modern study of approximate dynamic programming (DP) combines ideas from several research traditions. Among these is the field of Artificial Intelligence, whose earliest period focussed on creating artificial learning systems. Today, Machine Learning is an active branch of Artificial Intelligence (although it includes researchers from many other disciplines as well) devoted to continuing the development of artificial learning systems. Some of the problems studied in Machine Learning concern stochastic sequential decision processes, and some approaches to solving them are based on DP. These problems and algorithms fall under the general heading of reinforcement learning. In this chapter, we discuss stochastic sequential decision processes from the perspective of Machine Learning, focussing on reinforcement learning and its relationship to the more commmonly studied supervised learning problems. Machine Learning is the study ofmethods for constructing and improving software systems by analyzing examples of their behavior rather than by directly programming them. Machine Learning methods are appropriate in application settings where people are unable to provide precise specifications for desired program behavior, but where examples of desired behavior are available, or where it is possible to assign a measure of goodness to examples of behavior. Such situations include optical character recognition, handwriting recognition, speech recognition, automated steering of automobiles, and robot control and navigation. A key property of tasks in which examples of desired behavior are available is that people can perform them quite easily, but people cannot articulate exactly how they perform them. Hence, people
منابع مشابه
The Effect of Electronical Media on the Reinforcement of Social Behavior of Youth from the Computer Course Professors and Students Viewpoints of Sari Islamic Azad University
The goal of research was the effect of electronical learning media on the reinforcement of youth social behavior from the point of view of computer course professors and students of Islamic Azad University of Sari. The statistical population was included of all computer students and professors of I.A.U of Sari. The statistical sample was identified by using of the sample content identification ...
متن کاملAlgorithms and Representations for Reinforcement Learning
Machine Learning is a field of research aimed at constructing intelligent machines that gain and improve their skills by learning and adaptation. As such, Machine Learning research addresses several classes of learning problems, including for instance, supervised and unsupervised learning. Arguably, the most ubiquitous and realistic class of learning problems, faced by both living creatures and...
متن کاملLearning to Learn: Meta-Critic Networks for Sample Efficient Learning
We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning. The key idea is to learn a meta-critic: an action-value function neural network that learns to criticise any actor trying to solve any specified task. For sup...
متن کاملSelecting concise sets of samples for a reinforcement learning agent
We derive an algorithm for selecting from the set of samples gathered by a reinforcement learning agent interacting with a deterministic environment, a concise set from which the agent can extract a good policy. The reinforcement learning agent is assumed to extract policies from sets of samples by solving a sequence of standard supervised learning regression problems. To identify concise sets,...
متن کاملA Comparison of Supervised and Reinforcement Learning Methods on a Reinforcement Learning Task
The \forward modeling" approach of Jor-dan and Rumelhart has been shown to be applicable when supervised learning methods are to be used for solving reinforcement learning tasks. Because such tasks are natural candidates for the application of reinforcement learning methods, there is a need to evaluate the relative merits of these two learning methods on reinforcement learning tasks. We present...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003