You might also like

More about Adaptive Representations for Reinforcement Learning

• Book details
• Synopsis
• Trending among others

You get 249 loyalty points

Book synopsis

This book presents the main results new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks an effective control policy for tackling a sequential decision task. Unlike in supervised learning, the agent never sees examples of correct or incorrect behavior but receives only a reward signal as feedback. This book also introduces a novel method for devising input representations. In particular, it presents a way to find a minimal set of features sufficient to describe the agent s current state, a challenge known as the feature selection problem. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially§improve performance over methods with manual representations.

Book details

Book category Books in English Computing & information technology Computer science Artificial intelligence

• Full title: Adaptive Representations for Reinforcement Learning
• Author: Shimon Whiteson
• Language: English
• Binding: Hardback
• Number of pages: 116
• EAN: 9783642139314
• ISBN: 3642139310
• ID: 01656109
• Publisher: Springer-Verlag Berlin and Heidelberg GmbH & Co. KG
• Weight: 396 g
• Dimensions: 235 × 155 × 13 mm
• Date of publishing: 05. October 2010

Trending among others

---

---

---