José Antonio Martín H.
José Antonio Martín H.
Repsol Technology Lab
Dirección de correo verificada de fdi.ucm.es - Página principal
Título
Citado por
Citado por
Año
Dyna-H: A heuristic planning reinforcement learning algorithm applied to role-playing game strategy decision systems
M Santos, V López, G Botella
Knowledge-Based Systems 32, 28-36, 2012
45*2012
Orthogonal variant moments features in image analysis
M Santos, J de Lope
Information Sciences 180 (6), 846-860, 2010
452010
Robust high performance reinforcement learning through weighted k-nearest neighbors
J de Lope, D Maravall
Neurocomputing 74 (8), 1251-1259, 2011
402011
Adaptation, anticipation and rationality in natural and artificial systems: computational paradigms mimicking nature
J de Lope, D Maravall
Natural Computing 8 (4), 757, 2009
402009
A method to learn the inverse kinematics of multi-link robots by evolving neuro-controllers
JA Martín H, J de Lope, M Santos
Neurocomputing 72 (13), 2806-2814, 2009
372009
FPGA-based multimodal embedded sensor system integrating low-and mid-level vision
G Botella, JA Martín H, M Santos, U Meyer-Baese
Sensors 11 (8), 8164-8179, 2011
342011
Hybridizing evolutionary computation and reinforcement learning for the design of almost universal controllers for autonomous robots
D Maravall, J de Lope, JA Martín H
Neurocomputing 72 (4-6), 887-894, 2009
27*2009
Search and retrieval of plasma wave forms: Structural pattern recognition approach
S Dormido-Canto, G Farias, J Vega, R Dormido, J Sánchez, N Duro, ...
Review of scientific instruments 77 (10), 10F514, 2006
262006
The knn-td reinforcement learning algorithm
J de Lope, D Maravall
International Work-Conference on the Interplay Between Natural and …, 2009
242009
A distributed reinforcement learning architecture for multi-link robots
JA Martin H, J De Lope
4th International Conference on Informatics in Control, Automation and …, 2007
24*2007
Ex〈 α〉: An effective algorithm for continuous actions Reinforcement Learning problems
JA Martin H, J de Lope
Industrial Electronics, 2009. IECON'09. 35th Annual Conference of IEEE, 2063 …, 2009
20*2009
Learning autonomous helicopter flight with evolutionary reinforcement learning
J de Lope
International Conference on Computer Aided Systems Theory, 75-82, 2009
112009
Evolution of Neuro-controllers for Multi-link Robots
JA Martín H, J de Lope, M Santos
Innovations in Hybrid Intelligent Systems, 175-182, 2007
82007
Dynamic clustering and modeling approaches for fusion plasma signals
JA Martin H, MS Penas, G Farias, N Duro, J Sanchez, R Dormido, ...
Instrumentation and Measurement, IEEE Transactions on 58 (9), 2969-2978, 2009
7*2009
Solving Hard Computational Problems Efficiently: Asymptotic Parametric Complexity 3-Coloring Algorithm
JA Martın H
PLoS ONE 8 (1), e53437, 2013
62013
Analysis and solution of a predator-protector-prey multi-robot system by a high-level reinforcement learning architecture and the adaptive systems theory
JA Martín H, J De Lope, D Maravall
Robotics and Autonomous Systems 58 (12), 1266-1272, 2010
62010
A divisive hierarchical k-means based algorithm for image segmentation
JA Martin H, J Montero, J Yáñez, D Gomez
Intelligent Systems and Knowledge Engineering (ISKE), 2010 International …, 2010
6*2010
Applying reinforcement learning to multi-robot team coordination
Y Sanz, J de Lope
International Workshop on Hybrid Artificial Intelligence Systems, 625-632, 2008
62008
A k-NN based perception scheme for reinforcement learning
J de Lope
International Conference on Computer Aided Systems Theory, 138-145, 2007
62007
Linear Bayes policy for learning in contextual-bandits
JA Martín H., AM Vargas
Expert Systems with Applications 40 (18), 7400–7406, 2013
52013
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20