 | 2011 |
|---|
| 9 |       | Alejandro Agostini,
Enric Celaya:
A Competitive Strategy for Function Approximation in Q-Learning.
IJCAI 2011: 1146-1151 |
| 8 | | Alejandro Agostini,
Carme Torras,
Florentin Wörgötter:
Integrating Task Planning and Interactive Learning for Robots to Work in Human Environments.
IJCAI 2011: 2386-2391 |
| 7 | | Norbert Krüger,
Christopher W. Geib,
Justus H. Piater,
Ronald P. A. Petrick,
Mark Steedman,
Florentin Wörgötter,
Ales Ude,
Tamim Asfour,
Dirk Kraft,
Damir Omrcen,
Alejandro Agostini,
Rüdiger Dillmann:
Object-Action Complexes: Grounded abstractions of sensory-motor processes.
Robotics and Autonomous Systems 59(10): 740-757 (2011) |
| 2010 |
|---|
| 6 |  | Alejandro Agostini,
Enric Celaya:
Reinforcement Learning for Robot Control using Probability Density Estimations.
ICINCO (1) 2010: 160-168 |
| 5 | | Alejandro Agostini,
Enric Celaya:
Reinforcement Learning with a Gaussian mixture model.
IJCNN 2010: 1-8 |
| 2009 |
|---|
| 4 | | Alejandro Agostini,
Enric Celaya:
Exploiting Domain Symmetries in Reinforcement Learning with Continuous State and Action Spaces.
ICMLA 2009: 331-336 |
| 3 | | Florentin Wörgötter,
Alejandro Agostini,
Norbert Krüger,
N. Shylo,
Bernd Porr:
Cognitive agents - a procedural perspective relying on the predictability of Object-Action-Complexes (OACs).
Robotics and Autonomous Systems 57(4): 420-432 (2009) |
| 2005 |
|---|
| 2 | | Alejandro Agostini,
Enric Celaya:
Feasible control of complex systems using automatic learning.
ICINCO 2005: 284-287 |
| 2004 |
|---|
| 1 | | Alejandro Agostini,
Enric Celaya:
Learning Model Free Motor Control.
ECAI 2004: 947-948 |
Data released under the ODC-BY 1.0 license — See also our legal information page