Mikel Malagón

According to our database, Mikel Malagón authored at least 6 papers between 2019 and 2025.

Collaborative distances:

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

2025

Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments.

Mikel Malagón, Josu Ceberio, José Antonio Lozano

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

A Combinatorial Optimization Framework for Probability-Based Algorithms by Means of Generative Models.

Mikel Malagón, Ekhine Irurozki, Josu Ceberio

ACM Trans. Evol. Learn. Optim., September, 2024

Craftium: An Extensible Framework for Creating Reinforcement Learning Environments.

Mikel Malagón, Josu Ceberio, José Antonio Lozano

CoRR, 2024

Self-Composing Policies for Scalable Continual Reinforcement Learning.

Mikel Malagón, Josu Ceberio, José Antonio Lozano

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2020

Alternative Representations for Codifying Solutions in Permutation-Based Problems.

Mikel Malagón, Ekhine Irurozki, Josu Ceberio

Proceedings of the IEEE Congress on Evolutionary Computation, 2020

2019

Evolving Neural Networks in Reinforcement Learning by means of UMDAc.

Mikel Malagón, Josu Ceberio

CoRR, 2019