| |
|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNISOBSON0006348 |
|
|
Autore |
Maccari, Cesare |
|
|
Titolo |
Omiccioli in Argentina / Cesare Maccari |
|
|
|
|
|
Pubbl/distr/stampa |
|
|
|
|
|
|
Descrizione fisica |
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
2. |
Record Nr. |
UNINA9910346911203321 |
|
|
Autore |
Deisenroth Marc Peter |
|
|
Titolo |
Efficient Reinforcement Learning using Gaussian Processes |
|
|
|
|
|
Pubbl/distr/stampa |
|
|
KIT Scientific Publishing, 2010 |
|
|
|
|
|
|
|
ISBN |
|
|
|
|
|
|
Descrizione fisica |
|
1 online resource (IX, 205 p. p.) |
|
|
|
|
|
|
Collana |
|
Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory |
|
|
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
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. |
|
|
|
|
|
| |