Transfer in Reinforcement Learning: a Framework and a Survey

Alessandro Lazaric 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
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.
Document type :
Book sections
Complete list of metadatas

https://hal.inria.fr/hal-00772626
Contributor : Alessandro Lazaric <>
Submitted on : Thursday, January 10, 2013 - 6:51:33 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Thursday, April 11, 2013 - 4:08:54 AM

File

transfer.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

481

Files downloads

3028