Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Model–free least–squares policy iteration

Lagoudakis Michael, Parr, R.

Simple record


URIhttp://purl.tuc.gr/dl/dias/CDADBEEF-15F4-44B5-89B2-295FEC71FDAE-
Identifierhttp://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.22.4345&rep=rep1&type=pdf-
Languageen-
Extent8 pagesen
TitleModel–free least–squares policy iterationen
CreatorLagoudakis Michaelen
CreatorΛαγουδακης Μιχαηλel
CreatorParr, R.en
Content SummaryWe propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely o policy. We are motivated by the least squares temporal dierence learning algorithm (LSTD), which is known for its ecient use of sample experiences compared to pure temporal dierence algorithms. LSTD is ideal for prediction problems, however it heretofore has not had a straightforward application to control problems. Moreover, approximations learned by LSTD are strongly in uenced by the visitation distribution over states. Our new algorithm, Least-Squares Policy Iteration (LSPI) addresses these issues. The result is an o-policy method which can use (or reuse) data collected from any source. We test LSPI on several problems, including a bicycle simulator in which it learns to guide the bicycle to a goal eciently by merely observing a relatively small number of completely random trials. en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-11-14-
Date of Publication2001-
Subject Artificial Intelligenceen
Bibliographic CitationM. G. Lagoudakis and R. Parr. (2001, Dec.).Model–free least–squares policy iteration. [Online]. Available: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.22.4345&rep=rep1&type=pdfen

Services

Statistics