Efficient Reinforcement Learning using Gaussian Processes
This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model...
Saved in:
Main Author: | |
---|---|
Format: | Electronic Book Chapter |
Language: | English |
Published: |
KIT Scientific Publishing
2010
|
Series: | Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory
|
Subjects: | |
Online Access: | DOAB: download the publication DOAB: description of the publication |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
MARC
LEADER | 00000naaaa2200000uu 4500 | ||
---|---|---|---|
001 | doab_20_500_12854_45907 | ||
005 | 20210211 | ||
003 | oapen | ||
006 | m o d | ||
007 | cr|mn|---annan | ||
008 | 20210211s2010 xx |||||o ||| 0|eng d | ||
020 | |a KSP/1000019799 | ||
020 | |a 9783866445697 | ||
040 | |a oapen |c oapen | ||
024 | 7 | |a 10.5445/KSP/1000019799 |c doi | |
041 | 0 | |a eng | |
042 | |a dc | ||
100 | 1 | |a Deisenroth, Marc Peter |4 auth | |
245 | 1 | 0 | |a Efficient Reinforcement Learning using Gaussian Processes |
260 | |b KIT Scientific Publishing |c 2010 | ||
300 | |a 1 electronic resource (IX, 205 p. p.) | ||
336 | |a text |b txt |2 rdacontent | ||
337 | |a computer |b c |2 rdamedia | ||
338 | |a online resource |b cr |2 rdacarrier | ||
490 | 1 | |a Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory | |
506 | 0 | |a Open Access |2 star |f Unrestricted online access | |
520 | |a This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems. | ||
540 | |a Creative Commons |f https://creativecommons.org/licenses/by-nc-nd/4.0/ |2 cc |4 https://creativecommons.org/licenses/by-nc-nd/4.0/ | ||
546 | |a English | ||
653 | |a autonomous learning | ||
653 | |a Gaussian processes | ||
653 | |a control | ||
653 | |a machine learning | ||
653 | |a Bayesian inference | ||
856 | 4 | 0 | |a www.oapen.org |u https://www.ksp.kit.edu/9783866445697 |7 0 |z DOAB: download the publication |
856 | 4 | 0 | |a www.oapen.org |u https://directory.doabooks.org/handle/20.500.12854/45907 |7 0 |z DOAB: description of the publication |