Efficient Reinforcement Learning using Gaussian Processes
Karlsruhe Series on Intelligent Sensor Actuator Systems
, Volume 9
KIT Scientific Publishing
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.