Contribution to the study and the design of reinforcement functions
The underlying concept in Reinforcement Learning is as simple as it is attractive: to learn by trial and error from the interaction with the environment. This approach allows us to deal with problems where a learning technique searches to improve the performance of the agent (the learner) over time....
Guardado en:
Autor principal: | |
---|---|
Formato: | Articulo |
Lenguaje: | Español |
Publicado: |
2000
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/135464 https://publicaciones.sadio.org.ar/index.php/EJS/article/view/127 |
Aporte de: |
Sumario: | The underlying concept in Reinforcement Learning is as simple as it is attractive: to learn by trial and error from the interaction with the environment. This approach allows us to deal with problems where a learning technique searches to improve the performance of the agent (the learner) over time. Reinforcement Learning groups a set of such techniques, and it uses a performance measure based on two types of signals given by a Critic or Reinforcement Function: penalty and reward. |
---|