no code implementations • 4 Sep 2022 • Martin Biehl, Nathaniel Virgo
To do this we make use of the existing theory of partially observable Markov processes (POMDPs): we say that a system can be interpreted as a solution to a POMDP if it not only admits an interpretation map describing its beliefs about the hidden state of a POMDP but also takes actions that are optimal according to its belief state.
no code implementations • 27 Dec 2021 • Nathaniel Virgo, Martin Biehl, Simon McGregor
A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world.
no code implementations • 14 Jul 2021 • Francesco Massari, Martin Biehl, Lisa Meeden, Ryota Kanai
A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', which rewards the agent based on certain features of the current sensor state.
no code implementations • 5 Oct 2020 • Martin Biehl, Ryota Kanai
On the other hand we attempt to establish a connection between a quantity that is a feature of the interpretation of the hyperparameter as a model, namely the information gain, and the one-step pointwise NTIC which is a quantity that does not depend on this interpretation.
no code implementations • 28 Aug 2020 • Fernando E. Rosas, Pedro A. M. Mediano, Martin Biehl, Shamil Chandaria, Daniel Polani
We introduce a novel framework to identify perception-action loops (PALOs) directly from data based on the principles of computational mechanics.
no code implementations • 12 Jan 2020 • Martin Biehl, Felix A. Pollock, Ryota Kanai
Additionally, we highlight that the variational densities presented in newer formulations of the free energy principle and lemma are parameterised by different variables than in older works, leading to a substantially different interpretation of the theory.
no code implementations • 20 Nov 2018 • Martin Biehl
We reconstruct Karl Friston's active inference and give a geometrical interpretation of it.
no code implementations • 21 Jun 2018 • Martin Biehl, Christian Guckelsberger, Christoph Salge, Simón C. Smith, Daniel Polani
Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.
1 code implementation • 1 Jun 2018 • Nicholas Guttenberg, Martin Biehl, Nathaniel Virgo, Ryota Kanai
We investigate the use of attentional neural network layers in order to learn a `behavior characterization' which can be used to drive novelty search and curiosity-based policies.
1 code implementation • 15 Aug 2017 • Nicholas Guttenberg, Martin Biehl, Ryota Kanai
Controlling embodied agents with many actuated degrees of freedom is a challenging task.
no code implementations • 12 Jun 2017 • Martin Biehl, Daniel Polani
This is a contribution to the formalization of the concept of agents in multivariate Markov chains.
no code implementations • 10 Apr 2017 • Martin Biehl
We present a new measure that can be used to identify entities (called $\iota$-entities), some general requirements for entities in multivariate Markov chains, as well as formal definitions of actions and perceptions suitable for such entities.
no code implementations • 1 Sep 2016 • Nicholas Guttenberg, Martin Biehl, Ryota Kanai
We present a loss function for neural networks that encompasses an idea of trivial versus non-trivial predictions, such that the network jointly determines its own prediction goals and learns to satisfy them.
no code implementations • 18 May 2016 • Martin Biehl, Takashi Ikegami, Daniel Polani
We present some arguments why existing methods for representing agents fall short in applications crucial to artificial life.