Neural Networks and Statistical Learning by Ke-Lin Du & M. N. S. Swamy
Author:Ke-Lin Du & M. N. S. Swamy
Language: eng
Format: epub
ISBN: 9781447174523
Publisher: Springer London
17.5 Learning from Demonstrations
As a wrong action can result in unrecoverable effects, this poses a safety–exploration dilemma, especially for a model-free approach. A common approach to safety consists of assigning negative rewards for undesired transitions, such that the most reliable policy maximizes the minimal sum of reward in the presence of uncertainties and stochasticity, yielding a worst-case or minimax problem. By assigning a negative reward, the variance of the return can be taken into account by adopting risk-sensitivity approaches [31]. There are three approaches to safe exploration [12]:providing initial knowledge, directing the learning in its initial stage toward more profitable and safer regions of the state space;
Download
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.
Computer Vision & Pattern Recognition | Expert Systems |
Intelligence & Semantics | Machine Theory |
Natural Language Processing | Neural Networks |
Algorithms of the Intelligent Web by Haralambos Marmanis;Dmitry Babenko(7845)
Hadoop in Practice by Alex Holmes(5656)
Jquery UI in Action : Master the concepts Of Jquery UI: A Step By Step Approach by ANMOL GOYAL(5509)
Life 3.0: Being Human in the Age of Artificial Intelligence by Tegmark Max(4492)
Functional Programming in JavaScript by Mantyla Dan(3719)
The Age of Surveillance Capitalism by Shoshana Zuboff(3411)
Big Data Analysis with Python by Ivan Marin(2965)
Blockchain Basics by Daniel Drescher(2884)
The Rosie Effect by Graeme Simsion(2704)
WordPress Plugin Development Cookbook by Yannick Lefebvre(2580)
Hands-On Machine Learning for Algorithmic Trading by Stefan Jansen(2491)
Applied Predictive Modeling by Max Kuhn & Kjell Johnson(2474)
Dawn of the New Everything by Jaron Lanier(2433)
The Art Of Deception by Kevin Mitnick(2294)
Test-Driven Development with Java by Alan Mellor(2293)
Rapid Viz: A New Method for the Rapid Visualization of Ideas by Kurt Hanks & Larry Belliston(2189)
Human Dynamics Research in Smart and Connected Communities by Shih-Lung Shaw & Daniel Sui(2174)
Once Upon an Algorithm by Martin Erwig(2142)
Data Augmentation with Python by Duc Haba(2139)