| .: ÍNDICE |
Inicio
|
Docencia
|
Investigación
|
Publicaciones
|
|
|
|
|
|
PUBLICATIONS
Publications (contact me if you have problems to download any publication)
2010
- A Comparative Study of Discretization Approaches for State Space Generalization in the Keepaway Soccer Task. Javier García, Iván López-Bueno, Fernando Fernández y Daniel Borrajo. In Reinforcement Learning: Algorithms, Implementations and Aplications. Nova Science Publishers. 2010.
- A Reinforcement Learning approach for Multiagent Navigation. Francisco Martínez-Gil, Fernando Barber, Miguel Lozano, Francisco Grimaldo and Fernando Fernández. International Conference on Agents and Artificial Intelligence. 2010 (Accepted).
- Probabilistic Policy Reuse
for Inter-Task Transfer Learning. Fernando
Fernández, Javier García and Manuela Veloso. Robotics and Autonomous
Systems, Special Issue on Advances in Autonomous Robots for Service
and Entertainment. 2010.
- SIMBA: A Simulator for Business Education and Research . Fernando Borrajo, Yolanda Bueno, Isidro de Pablo, Begoña Santos, Fernando Fernández, Javier García and Ismael Sagredo. Decision Support Systems 48, pp 498-506. Elsevier 2010.
2009
- Nearest Prototype Classification of Noisy Data. Fernando Fernández and Pedro Isasi. Artificial Intelligence Review 30. 2009. DOI 10.1007/s10462-009-9116-7
- Three Relational Learning Approaches for Lookahead Heuristic Planning. Tomás de la Rosa and Sergio Jiménez and Rocío García-Durán and Fernando Fernández and Angel García-Olaya and Daniel Borrajo. {Proceedings of the ICAPS'09 Workshop on Planning and Learning, 2009.
- On Compiling Data Mining Tasks to PDDL. Susana Fernández and Fernando Fernández and Alexis Sánchez and Tomás de la Rosa and Javier Ortiz and Daniel Borrajo and David Manzano. Proceedings of the International Competition on Knoweldge Engieering for Planning and Schedulling (ICKEPS'09), 2009.
- Assisting Data Mining through Automated Planning. Fernando Fernández, Daniel Borrajo, Susana Fernández and David Manzano. Machine Learning and Data Mining 2009 (MLDM 2009). Lecture Notes in Artificial Intelligence 5632, pp 760-774. Springer-Verlag 2009.
- Two Steps Reinforcement Learning in Continuous Reinforcement Learning Tasks. Iván López-Bueno and Javier García and Fernando Fernández. 10th International Work-Conference on Artificial Neural Networks (IWANN 2009). Lecture Notes in Computer Science 5517, pp 577-584. 2009.
- Reinforcement Learning of Pedagogical Policies in Adaptive and Intelligent Educational Systems. Ana Iglesias, Paloma Martínez, Ricardo Aler, Fernando Fernández. Knowledge Based Systems 22(4), pp 266-270. 2009.
- Learning Teaching Strategies in an Adaptive and Intelligent Educational System through Reinforcement Learning. Ana Iglesias, Paloma Martínez, Ricardo Aler, Fernando Fernández. Applied Intelligence 31(1), pp 89-106. 2009.
2008
- Learning and Transferring Relational Instance-Based Policies. Rocío García-Durán, Fernando Fernández and Daniel Borrajo. Transfer Learning for Complex Task Workshop of the AAAI'08, Technical Report WS-08-13, pp 19-24. AAAI Press 2008.
- Prototypes Based Relational Learning. Rocío García-Durán, Fernando Fernández and Daniel Borrajo. The 13th International Conference on Artificial Intelligence: Methodology, Systems, Applications (AIMSA'08). Lecture Notes in Artificial Intelligence 5253, pp 130-143. Springer-Verlag 2008.
- Local Feature Weighting in Nearest Prototype Classification. Fernando Fernández and Pedro Isasi. IEEE Transactions on Neural Networks 19(1), pp 40-53. 2008.
- Two Steps Reinforcement Learning. Fernando Fernáandez and Daniel Borrajo. International Journal of Intelligent Systems 23(2), pp 213-245. 2008.
- The PELA architecture: integrating planning and learning to improve execution. Sergio Jiménez and Fernando Fernández and Daniel Borrajo. Proceedings of the AAAI'08. 2008.
2007
- Reinforcement Learning in the RoboCup-Soccer Keepaway. Francisco Javier García, Manuela Veloso and Fernando Fernández. Proceedings of the 12th Conference of the Spanish Association for Artificial Intelligence (CAEPIA'07+TTIA). 2007.
- Learning Action Durations from Executions. Jesús Lanchas, Sergio Jiménez, Fernando Fernández and Daniel Borrajo. Proceedings of the ICAPS-07 Workshop on AI Planning and Learning (AIPL-07). 2007.
- Combining Macro-operators with Control Knowledge . Rocío García-Durán, Fernando Fernández and Daniel Borrajo. 16th International Conference on Inductive Logic Programming (ILP'06). Lecture Notes in Artificial Intelligence 4455, pp 229-244. Springer-Verlag 2007.
2006
- Learning Pedagogical Policies from Reduced Experience . Ana Iglesias, Paloma Martínez, Ricardo Aler and Fernando Fernández . ECAI'06 Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds. August 2006.
- Nearest Prototype Classification for Relational Learning . Rocío García-Durán, Fernando Fernández and Daniel Borrajo. 16th International Conference on Inductive Logic Programming (ILP'06). August 2006.
- Policy Reuse for Transfer Learning Across Tasks with DifferentState and Action Spaces . Fernando Fernández and Manuela Veloso. ICML'06 Workshop on Structural Knowledge Transfer for Machine Learning. June 2006.
- Reusing and Building Policy Libraries . Fernando Fernández and Manuela Veloso. Proceedings of the International Conference on Automated Planning and Schedulling (ICAPS'06). June 2006.
- Probabilistic Policy Reuse in a Reinforcement Learning Agent. Fernando Fernández and Manuela Veloso. Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS'06). May 2006.
- Roboskeleton: An Architecture for Coordinating Robot Soccer Agents David Camacho, Fernando Fernández and Miguel Ángel Rodelgo. Engineering Applications of Artificial Intelligence 19(2), pp 179-188. 2006.
2005
- Machine learning of plan robustness knowledge about instances. Sergio Jiménez, Fernando Fernández and Daniel Borrajo. In Proceedings of the European Conference on Machine Learning (ECML'05). October 2005.
- Building a Library of Policies through Policy Reuse . Fernando Fernández and Manuela Veloso. Technical Report CMU-CS-05-174. Computer Science Department, Carnegie Mellon University. July 2005.
- Learning by Probabilistic Reuse of Past Policies . Fernando Fernández and Manuela Veloso. Technical Report CMU-CS-05-173. Computer Science Department, Carnegie Mellon University. July 2005.
- Exploration and Policy Reuse . Fernando Fernández and Manuela Veloso. Technical Report CMU-CS-05-172. Computer Science Department, Carnegie Mellon University. July 2005.
- A Reinforcement Learning Algorithm in Cooperative Multi-Robot Domains. Fernando
Fernández, Daniel
Borrajo and Lynne
Parker. Journal of Intelligent Robotics Systems, 2005.
- Capturing knowledge about the instances behavior in
probabilistic domains . Sergio Jiménez, Fernando Fernández and Daniel Borrajo. PLANSIG-05. Pages 44-51. 2005.
2004
-
Evolutionary Design of Nearest Prototype Classifiers. Fernando
Fernández and Pedro Isasi. In Journal of Heuristics 10(4).
2004.
- Learning Content Sequencing in an Educational Environment According Student Need. Ana Iglesias ,
Paloma Martínez, Ricardo Aler and Fernando
Fernández . In Algorithmic Learning Theory: 15th International Conference, ALT 2004. Lecture Notes on Computer Sciences 3244. Pages 454 - 463. Springer-Verlag. 2004
2003
- An Experience Applying Reinforcement Learning in a Web-based Adaptive and
Intelligent Educational System. Ana Iglesias ,
Paloma Martínez and Fernando
Fernández . In Informatics in Education, I.J. 2. 2003.
- Evolutionary Approach to Overcome Initialization Parameters in Classification Problems. Pedro Isasi and Fernando
Fernández . Computational Methods in Neural Modelling. Lecture Notes in Computer Sciences 2686, pp 254-261. Springer-Verlag. 2003
- From Continuous Behaviour to Discrete Knowledge.. Agapito Ledezma, Fernando
Fernández and Ricardo Aler. Artificial Neural Nets Problem Solving Methods (IWANN 2003). Lecture Notes in Computer Sciences 2687, pp 217-224. Springer-Verlag. 2003
- Analising the Advantages of Using Exploration and Exploitation Strategies in an Adaptive and Intelligent Educational System. Ana Iglesias ,
Paloma Martínez, Ricardo Aler and Fernando
Fernández . In Proceedings of the Second International Conference on Multimedia and Information & Communication Technologies in Education (m-ICTE 2003). Pages 489-493. 2003
- Navigating Through the RLATES Interface: A Web-based Adaptive and Intelligentet Educational System. Ana Iglesias ,
Paloma Martínez and Fernando
Fernández . In On the Move to Meaningful Internet Systems 2003: OTM 2003 workshops. Lecture Notes in Computer Sciences 2889. Pages 175-184. Springer-Verlag. 2003
2002
- On
Determinism Handling While Learning State Space Representations. Fernando
Fernández ,Daniel
Borrajo. In Proceedings of the European Conference on Artificial
Intelligence (ECAI'02). Lyon. France. 2002.
- Applying Reinforcement Learning in Intelligent Tutoring Systems. Ana Iglesias ,
Paloma Martínez and Fernando
Fernández . In Proceedings of the Fourth International Conference on New Educational Environment (ICNEE 2002). Pages 11-14. 2002.
- Learning to Teach Database Design by Trial and Error Ana Iglesias ,
Paloma Martínez, Dolores Cuadra, Elena Castro and Fernando
Fernández . In Proceedings of the 4th International Conference on Enterprise Information Systems (ICEIS 2002). Pages 500-505. 2002.
- Automatic Finding of Good Classifiers Following a Biologically Inspired Metaphor. Fernando
Fernández and Pedro Isasi. In Computing and Informatics 21(3). 2002. Pages 205-220. 2002.
2001
- Techniques for Learning in Multi-Robot Teams. Lynne Parker, Claude Touzet and Fernando
Fernández. Techniques for Learning in Multi-Robot
Teams, Robot Teams: From Diversity to Polymorphism, Tucker Balch and Lynne
E. Parker (eds.), A K Peters, 2001.
- Learning in Large Cooperative Multi-Robot Domains. Fernando Fernández , Lynne Parker. International Journal of Robotics and Automation, special issue on Computational Intelligence Techniques in Cooperative Robots, 16 (4), pages 217-226, 2001.
- Designing Nearest Neighbour Classifiers by the Evolution of a Population of Prototypes. Fernando Fernández, Pedro Isasi. In Proceedings of the European Symposium on Artificial Neural Networks, pp. 171-178, Bruges - April 25-27, 2001.
2000
- VQQL. Applying Vector Quantization to Reinforcement Learning. Fernando Fernández , Daniel Borrajo. In Lecture Notes in Artificial Intelligence 1856. Pages 292-303. M.Veloso, E. Pagello and Hiroaki Kitano Eds. Springer Verlag, 2000.
- Iterative VQQL for Learning Skills . Fernando Fernández and Daniel Borrajo. In Proceedings of Learning'00. Leganes, Madrid, Spain. 2000.
1999
- Vector Quantization Applied to Reinforcement Learning. Fernando Fernández and Daniel Borrajo. In Working notes of the IJCAI'99 Workshop on RoboCup. Stockholm, Sweden. August, 1999.
|
|
|
|
|
|
|
