Under what circumstances can a system be said to have beliefs and goals,...
A central concept in active inference is that the internal states of a
p...
Reinforcement Learning (RL) is known to be often unsuccessful in environ...
We investigate the non-trivial informational closure (NTIC) of a Bayesia...
We introduce a novel framework to identify perception-action loops (PALO...
We reconstruct Karl Friston's active inference and give a geometrical
in...
Active inference is an ambitious theory that treats perception, inferenc...
We investigate the use of attentional neural network layers in order to ...
Controlling embodied agents with many actuated degrees of freedom is a
c...
This is a contribution to the formalization of the concept of agents in
...
This thesis contributes to the formalisation of the notion of an agent w...
We present a loss function for neural networks that encompasses an idea ...