Efficient Reinforcement Learning using Gaussian Processes

Format:

Book

Author/Creator:

Deisenroth, Marc Peter

Series:

Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory

Language:

English

Physical Description:

1 online resource (IX, 205 p. p.)

Place of Publication:

KIT Scientific Publishing 2010

Language Note:

English

Summary:

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.

ISBN:

1-000-01979-9