Efficient Reinforcement Learning using Gaussian Processes

• Autore: Deisenroth Marc Peter
• Pubblicazione: KIT Scientific Publishing, 2010
• Descrizione fisica: 1 online resource (IX, 205 p. p.)
• Soggetto non controllato: autonomous learning; Bayesian inference; control; Gaussian processes; machine learning
• Sommario/riassunto: 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.
• Titolo autorizzato: Efficient Reinforcement Learning using Gaussian Processes
• ISBN: 1-000-01979-9
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910346911203321
• Lo trovi qui: Univ. Federico II