Transfer in reinforcement learning domains [electronic resource] / Matthew E. Taylor.

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow...

Full description

Bibliographic Details

Online Access:	Full Text (via Springer)
Main Author:	Taylor, Matthew E.
Format:	Electronic eBook
Language:	English
Published:	Berlin : Springer, ©2009.
Series:	Studies in computational intelligence ; v. 216.
Subjects:	Reinforcement learning.