Transfer in Reinforcement Learning: a Framework and a Survey - Archive ouverte HAL Access content directly
Book Sections Year : 2012

Transfer in Reinforcement Learning: a Framework and a Survey

Alessandro Lazaric

Abstract

Transfer in reinforcement learning is a novel research area that focuses on the development of methods to transfer knowledge from a set of source tasks to a target task. Whenever the tasks are \textit{similar}, the transferred knowledge can be used by a learning algorithm to solve the target task and significantly improve its performance (e.g., by reducing the number of samples needed to achieve a nearly optimal performance). In this chapter we provide a formalization of the general transfer problem, we identify the main settings which have been investigated so far, and we review the most important approaches to transfer in reinforcement learning.
Fichier principal
Vignette du fichier
transfer.pdf (428.94 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00772626 , version 1 (10-01-2013)

Identifiers

Cite

Alessandro Lazaric. Transfer in Reinforcement Learning: a Framework and a Survey. Marco Wiering, Martijn van Otterlo. Reinforcement Learning - State of the art, 12, Springer, pp.143-173, 2012, ⟨10.1007/978-3-642-27645-3_5⟩. ⟨hal-00772626⟩
322 View
4661 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More