Travelled to:1 × Australia
1 × Finland
1 × Germany
1 × USA
Collaborated with:S.Dzeroski K.Kersting J.Ramon Samuel Sarjant B.Pfahringer Tony Smith
Talks about:relat (5) learn (4) base (3) reinforc (2) regress (2) instanc (2) polici (2) experiment (1) treatment (1) proposit (1)
Person: Kurt Driessens
DBLP: Driessens:Kurt
Contributed to:
2008200520032002
2011Wrote 5 papers:
- ICML-2008-KerstingD #parametricity #policy #relational
- Non-parametric policy gradients: a unified treatment of propositional and relational domains (KK, KD), pp. 456–463.
- ICML-2005-DriessensD #first-order #learning #modelling
- Combining model-based and instance-based learning for first order regression (KD, SD), pp. 193–200.
- ICML-2003-DriessensR #learning #relational
- Relational Instance Based Regression for Relational Reinforcement Learning (KD, JR), pp. 123–130.
- ICML-2002-DriessensD #learning #relational
- Integrating Experimentation and Guidance in Relational Reinforcement Learning (KD, SD), pp. 115–122.
- CIG-2011-SarjantPDS #game studies #online #policy #relational #using
- Using the online cross-entropy method to learn relational policies for playing different games (SS, BP, KD, TS), pp. 182–189.