Slika omota

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...

Cijeli opis

Spremljeno u:
Glavni autor: Deisenroth, Marc Peter
Format: Online
Jezik:engleski
Izdano: KIT Scientific Publishing 2021
Teme:
QA75.5-76.95
autonomous learning
Gaussian processes
control
machine learning
Bayesian inference
bic Book Industry Communication::U Computing & information technology::UY Computer science
Online pristup:35389
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!
Sažetak: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.

Slični predmeti