Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Model–free least–squares policy iteration

Lagoudakis Michael, Parr, R.

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/CDADBEEF-15F4-44B5-89B2-295FEC71FDAE-
Αναγνωριστικόhttp://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.22.4345&rep=rep1&type=pdf-
Γλώσσαen-
Μέγεθος8 pagesen
ΤίτλοςModel–free least–squares policy iterationen
ΔημιουργόςLagoudakis Michaelen
ΔημιουργόςΛαγουδακης Μιχαηλel
ΔημιουργόςParr, R.en
ΠερίληψηWe 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
ΤύποςΠλήρης Δημοσίευση σε Συνέδριοel
ΤύποςConference Full Paperen
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2015-11-14-
Ημερομηνία Δημοσίευσης2001-
Θεματική Κατηγορία Artificial Intelligenceen
Βιβλιογραφική ΑναφοράM. 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

Υπηρεσίες

Στατιστικά