Yayınlanmış 1 Ocak 2006
| Sürüm v1
Konferans bildirisi
Açık
Learning by Automatic Option Discovery from Conditionally Terminating Sequences
Oluşturanlar
- 1. Middle East Tech Univ, TR-06531 Ankara, Turkey
Açıklama
This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learning framework to improve the learning performance. The method utilizes stored histories of possible optimal policies and constructs a specialized tree structure online in order to identify action sequences which are used frequently together with states that are visited during the execution of such sequences. The tree is then used to implicitly run corresponding options. Effectiveness of the method is demonstrated empirically.
Dosyalar
bib-e99e3b1b-46a8-4fcf-a3fd-bdd73fcf8857.txt
Dosyalar
(146 Bytes)
| Ad | Boyut | Hepisini indir |
|---|---|---|
|
md5:e5de6da1a346eec0d706569bf9c9aaba
|
146 Bytes | Ön İzleme İndir |