This paper analyzes Reinforcement Learning and its applications in robotics. After defining the particular learning technique and its main elements, the most important variants are described, followed by examples. Finally, there is a comparison between different documents that use Reinforcement Learning to solve common problems, highlighting their advantages and disadvantages.
Con questo elaborato si analizza il Reinforcement Learning e le sue applicazioni nella robotica. Dopo aver definito la particolare tecnica di apprendimento e i suoi principali elementi, vengono descritte le varianti più importanti, accompagnate da esempi. Infine si confrontano diversi documenti che usano il Reinforcement Learning per la soluzione di problemi di carattere comune, evidenziandone vantaggi e svantaggi.
REINFORCEMENT LEARNING: STATO DELL'ARTE SU TECNOLOGIE E APPLICAZIONI
DI MODUGNO, ROCCO
2019/2020
Abstract
This paper analyzes Reinforcement Learning and its applications in robotics. After defining the particular learning technique and its main elements, the most important variants are described, followed by examples. Finally, there is a comparison between different documents that use Reinforcement Learning to solve common problems, highlighting their advantages and disadvantages.I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14253/77816