Travelled to:1 × Canada
1 × Germany
2 × USA
Collaborated with:A.G.Barto A.P.Wolfe J.Neville D.Jensen J.Komoroske K.Palmer H.G.Goldberg
Talks about:use (4) reinforc (2) identifi (2) relat (2) learn (2) discoveri (1) knowledg (1) abstract (1) subgoal (1) prevent (1)
Person: Özgür Simsek
DBLP: Simsek:=Ouml=zg=uuml=r
Contributed to:
20062005
20052004Wrote 4 papers:
- ICML-2006-SimsekB #performance
- An intrinsic reward mechanism for efficient exploration (ÖS, AGB), pp. 833–840.
- ICML-2005-SimsekWB #clustering #graph #identification #learning
- Identifying useful subgoals in reinforcement learning by local graph partitioning (ÖS, APW, AGB), pp. 816–823.
- KDD-2005-NevilleSJKPG #information management #relational #using
- Using relational knowledge discovery to prevent securities fraud (JN, ÖS, DJ, JK, KP, HGG), pp. 449–458.
- ICML-2004-SimsekB #abstraction #identification #learning #using
- Using relative novelty to identify useful temporal abstractions in reinforcement learning (ÖS, AGB).