Efficient Reinforcement Learning Using Gaussian Processes
- Marc Peter Deisenroth
Paperback & Hardcover deals ―
Amazon IndiaGOFlipkart GOSnapdealGOSapnaOnlineGOJain Book AgencyGOBooks Wagon₹1,701Book ChorGOCrosswordGODC BooksGOe-book & Audiobook deals ―
Amazon India GOGoogle Play Books GOAudible GO* Price may vary from time to time.
* GO = We're not able to fetch the price (please check manually visiting the website).
Know about the book -
Efficient Reinforcement Learning Using Gaussian Processes is written by Marc Peter Deisenroth and published by KIT Scientific Publishing. It's available with International Standard Book Number or ISBN identification 3866445695 (ISBN 10) and 9783866445697 (ISBN 13).
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.
