José Antonio Martín H.

According to our database, José Antonio Martín H. authored at least 32 papers between 2005 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

Reinforcement Learning in System Identification.

Jose Antonio Martin H., Oscar Fernández Vicente, Sergio Pérez, Anas Belfadil, Cristina Ibáñez-Llano, Freddy Jose Perozo Rondon, Jose Javier Valle, Javier Arechalde Pelaz

CoRR, 2022

2013

Linear Bayes policy for learning in contextual-bandits.

José Antonio Martín H., Ana M. Vargas

Expert Syst. Appl., 2013

2012

Dyna-H: A heuristic planning reinforcement learning algorithm applied to role-playing game strategy decision systems.

Matilde Santos, José Antonio Martín H., Victoria López, Guillermo Botella

Knowl. Based Syst., 2012

2011

FPGA-Based Multimodal Embedded Sensor System Integrating Low- and Mid-Level Vision.

Guillermo Botella, José Antonio Martín H., Matilde Santos, Uwe Meyer-Baese

Sensors, 2011

Robust high performance reinforcement learning through weighted k-nearest neighbors.

José Antonio Martín H., Javier de Lope Asiaín, Darío Maravall

Neurocomputing, 2011

A parametric-complexity exact 3-(UN)COLORING Algorithm

José Antonio Martín H.

CoRR, 2011

Minimal non-extensible precolorings and implicit-relations

José Antonio Martín H.

CoRR, 2011

A polynomial 3-colorability algorithm with automatic generation of NO 3-colorability (i.e. Co-NP) short proofs

Jose Antonio Martin H.

CoRR, 2011

Dyna-H: a heuristic planning reinforcement learning algorithm applied to role-playing-game strategy decision systems

Matilde Santos, José Antonio Martín H., Victoria López

CoRR, 2011

2010

Analysis and solution of a predator-protector-prey multi-robot system by a high-level reinforcement learning architecture and the adaptive systems theory.

José Antonio Martín H., Javier de Lope Asiaín, Darío Maravall

Robotics Auton. Syst., 2010

Erratum to 'Orthogonal variant moments features in image analysis' [Information Sciences 180 (2010) 846-860].

José Antonio Martín H., Matilde Santos Peñas, Javier de Lope Asiaín

Inf. Sci., 2010

Orthogonal variant moments features in image analysis.

José Antonio Martín H., Matilde Santos Peñas, Javier de Lope Asiaín

Inf. Sci., 2010

2009

Dynamic Clustering and Modeling Approaches for Fusion Plasma Signals.

José Antonio Martín H., Matilde Santos Peñas, Gonzalo Farias, Natividad Duro, José Sánchez Moreno, Raquel Dormido, Sebastián Dormido-Canto, Jesús Vega, Héctor Vargas

IEEE Trans. Instrum. Meas., 2009

Adaptation, anticipation and rationality in natural and artificial systems: computational paradigms mimicking nature.

José Antonio Martín H., Javier de Lope Asiaín, Darío Maravall

Nat. Comput., 2009

A model for the dynamic coordination of multiple competing goals.

José Antonio Martín H., Javier de Lope Asiaín

J. Exp. Theor. Artif. Intell., 2009

Hybridizing evolutionary computation and reinforcement learning for the design of almost universal controllers for autonomous robots.

Darío Maravall, Javier de Lope Asiaín, José Antonio Martín H.

Neurocomputing, 2009

A method to learn the inverse kinematics of multi-link robots by evolving neuro-controllers.

José Antonio Martín H., Javier de Lope Asiaín, Matilde Santos Peñas

Neurocomputing, 2009

Learning to Coordinate Multi-robot Competitive Systems by Stimuli Adaptation.

José Antonio Martín H., Javier de Lope Asiaín, Darío Maravall

Proceedings of the Bioinspired Applications in Artificial and Natural Computation, 2009

The kNN-TD Reinforcement Learning Algorithm.

José Antonio Martín H., Javier de Lope Asiaín, Darío Maravall

Proceedings of the Methods and Models in Artificial and Natural Computation. A Homage to Professor Mira.s Scientific Legacy, 2009

Learning Autonomous Helicopter Flight with Evolutionary Reinforcement Learning.

José Antonio Martín H., Javier de Lope Asiaín

Proceedings of the Computer Aided Systems Theory, 2009

2008

Evolution of Neuro-controllers for Multi-link Robots.

José Antonio Martín H., Javier de Lope Asiaín, Matilde Santos Peñas

Proceedings of the Innovations in Hybrid Intelligent Systems, 2008

A Computational Model of the Equivalence Class Formation Psychological Phenomenon.

José Antonio Martín H., Matilde Santos Peñas, Andrés García, Javier de Lope Asiaín

Proceedings of the Innovations in Hybrid Intelligent Systems, 2008

Applying Reinforcement Learning to Multi-robot Team Coordination.

Yolanda Sanz, Javier de Lope Asiaín, José Antonio Martín H.

Proceedings of the Hybrid Artificial Intelligence Systems, Third International Workshop, 2008

2007

Combining the Best of the Two Worlds: Inheritance Versus Experience.

Darío Maravall, Javier de Lope Asiaín, José Antonio Martín H.

Proceedings of the Nature Inspired Problem-Solving Methods in Knowledge Engineering, 2007

Concepts and Models for the Future Generation of Emotional and Intelligent Systems.

José Antonio Martín H., Javier de Lope Asiaín

Proceedings of the Bio-inspired Modeling of Cognitive Tasks, 2007

A distributed reinforcement learning control architecture for multi-link robots - experimental validation.

José Antonio Martín H., Javier de Lope Asiaín

Proceedings of the ICINCO 2007, 2007

A k-NN Based Perception Scheme for Reinforcement Learning.

José Antonio Martín H., Javier de Lope Asiaín

Proceedings of the Computer Aided Systems Theory, 2007

Helicopter Flight Dynamics Using Soft Computing Models.

Javier de Lope Asiaín, Juan José San Martín, José Antonio Martín H.

Proceedings of the Computer Aided Systems Theory, 2007

2006

Dynamic goal coordination in physical agents.

José Antonio Martín H., Javier de Lope Asiaín

Proceedings of the ICINCO 2006, 2006

2005

Search space modulation in genetic algorithms: evolving the search space by sinusoidal transformations.

José Antonio Martín H.

Proceedings of the Genetic and Evolutionary Computation Conference, 2005

A fuzzy expression processor with modifiers and hedges, conceptual design and tests.

José Antonio Martín H., Teresa de Pedro, Ricardo García Rosa, Carlos González

Proceedings of the Joint 4th Conference of the European Society for Fuzzy Logic and Technology and the 11th Rencontres Francophones sur la Logique Floue et ses Applications, 2005

Fuzzy Modeling for Coal Seams A Case Study for a Hard-Coal Mine.

José Antonio Martín H., Teresa de Pedro, Carlos González, Ricardo García Rosa, Luís Argüelles, Jose Rivas, Javier Toraño

Proceedings of the Computer Aided Systems Theory, 2005