Author

Esther Mondragón

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solving

This paper advocates category theory as a practical framework for structuring and improving rein- forcement learning in high-dimensional, partially observable environments by partitioning the state space into equivalence classes induced by sym- metry orbits, and organising each such class as a groupoid with a designate...

Ben Opperman, E. Alonso, Esther Mondragón · 0 citations

#artificial intelligence Preprint Sep 2026

Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries

Empirical results demonstrate that the proposed groupoid-based approach improves sample efficiency and convergence in dense and large-scale environments exhibiting strong partial symmetries, yielding substantial performance gains over standard Q-learning.

Ben Opperman, E. Alonso, Esther Mondragón · 2 citations