| 000 -LEADER |
|---|
| fixed length control field |
nam a22 7a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
180820b xxu||||| |||| 00| 0 eng d |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
|---|
| International Standard Book Number |
9781608454921 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
006.31 |
| Item number |
SZE |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Szepesvari, Csaba |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
Algorithms for reinforcement learning |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) |
|---|
| Name of publisher, distributor, etc |
Morgan & Claypool, |
| Date of publication, distribution, etc |
2010 |
| Place of publication, distribution, etc |
UK: |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
xii, 89 p. : |
| Other physical details |
ill.; |
| Dimensions |
23.5 cm. |
| 365 ## - TRADE PRICE |
|---|
| Price type code |
US$ |
| Price amount |
35.00 |
| 504 ## - BIBLIOGRAPHY, ETC. NOTE |
|---|
| Bibliography, etc |
Includes bibliographical references. |
| 520 ## - SUMMARY, ETC. |
|---|
| Summary, etc |
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name as entry element |
Machine learning |
|
|---|
| Topical term or geographic name as entry element |
Natural gradient |
|
|---|
| Topical term or geographic name as entry element |
Policy gradient |
|
|---|
| Topical term or geographic name as entry element |
Actor-critic methods |
|
|---|
| Topical term or geographic name as entry element |
Q-learning |
|
|---|
| Topical term or geographic name as entry element |
PAC-learning |
|
|---|
| Topical term or geographic name as entry element |
Planning |
|
|---|
| Topical term or geographic name as entry element |
Simulation |
|
|---|
| Topical term or geographic name as entry element |
Online learning |
|
|---|
| Topical term or geographic name as entry element |
Active learning |
|
|---|
| Topical term or geographic name as entry element |
Bias-variance tradeoff |
|
|---|
| Topical term or geographic name as entry element |
Overfitting |
|
|---|
| Topical term or geographic name as entry element |
Least-squares methods |
|
|---|
| Topical term or geographic name as entry element |
Stochastic gradient methods |
|
|---|
| Topical term or geographic name as entry element |
Function approximation |
|
|---|
| Topical term or geographic name as entry element |
Simulation optimization |
|
|---|
| Topical term or geographic name as entry element |
Two-timescale stochastic approximation |
|
|---|
| Topical term or geographic name as entry element |
Monte-Carlo methods |
|
|---|
| Topical term or geographic name as entry element |
Stochastic approximation |
|
|---|
| Topical term or geographic name as entry element |
Mathematical models |
|
|---|
| Topical term or geographic name as entry element |
Temporal difference learning |
|
|---|
| Topical term or geographic name as entry element |
Engineering & Applied Sciences |
|
|---|
| Topical term or geographic name as entry element |
Markov decision processes |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
|
| Item type |
Books |