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:
Superior document: | Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory |
---|---|
: | |
Year of Publication: | 2010 |
Language: | English |
Series: | Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory
|
Physical Description: | 1 electronic resource (IX, 205 p. p.) |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 01617nam-a2200337z--4500 | ||
---|---|---|---|
001 | 993545542804498 | ||
005 | 20231214133457.0 | ||
006 | m o d | ||
007 | cr|mn|---annan | ||
008 | 202102s2010 xx |||||o ||| 0|eng d | ||
020 | |a 1-000-01979-9 | ||
035 | |a (CKB)4920000000101410 | ||
035 | |a (oapen)https://directory.doabooks.org/handle/20.500.12854/45907 | ||
035 | |a (EXLCZ)994920000000101410 | ||
041 | 0 | |a eng | |
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 | |
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. | ||
546 | |a English | ||
653 | |a autonomous learning | ||
653 | |a Gaussian processes | ||
653 | |a control | ||
653 | |a machine learning | ||
653 | |a Bayesian inference | ||
776 | |z 3-86644-569-5 | ||
906 | |a BOOK | ||
ADM | |b 2023-12-15 05:55:13 Europe/Vienna |f system |c marc21 |a 2019-11-10 04:18:40 Europe/Vienna |g false | ||
AVE | |i DOAB Directory of Open Access Books |P DOAB Directory of Open Access Books |x https://eu02.alma.exlibrisgroup.com/view/uresolver/43ACC_OEAW/openurl?u.ignore_date_coverage=true&portfolio_pid=5338015360004498&Force_direct=true |Z 5338015360004498 |b Available |8 5338015360004498 |