4 papers
Integrated Information in the Active Inference Framework
Carlotta Langer, Jesse van Oostrum, Nihat Ay
The active inference framework provides a principled approach to modeling sentient behavior. In this framework perception and action selection are treated in a unified way. The res…
Dynamics-Aligned Shared Hypernetworks for Contextual RL under Discontinuous Shifts
Jan Benad, Pradeep Kr. Banerjee, Frank Röder +3
Zero-shot generalization in contextual reinforcement learning remains a core challenge, particularly when the context is latent and must be inferred from data. A canonical failure…
A Concise Mathematical Description of Active Inference in Discrete Time
Jesse van Oostrum, Carlotta Langer, Nihat Ay
In this paper we present a concise mathematical description of active inference in discrete time. The main part of the paper serves as a basic introduction to the topic, including…
Torsion of -connections on the density manifold
Nihat Ay, Lorenz J. Schwachhöfer
We study the torsion of the -connections defined on the density manifold in terms of a regular Riemannian metric. In the case of the Fisher-Rao metric our results confirm the f…