Search Results for author:
Found 14 papers, 2 papers with code
Interpreting systems as solving POMDPs: a step towards a formal understanding of agency
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.
Interpreting Dynamical Systems as Bayesian Reasoners
A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world.
Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments
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.
Non-trivial informational closure of a Bayesian hyperparameter
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.
Causal blankets: Theory and algorithmic framework
We introduce a novel framework to identify perception-action loops (PALOs) directly from data based on the principles of computational mechanics.
A Technical Critique of Some Parts of the Free Energy Principle
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.
Geometry of Friston's active inference
We reconstruct Karl Friston's active inference and give a geometrical interpretation of it.
Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.
Being curious about the answers to questions: novelty search with learned attention
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.
Learning body-affordances to simplify action spaces
Controlling embodied agents with many actuated degrees of freedom is a challenging task.
Action and perception for spatiotemporal patterns
This is a contribution to the formalization of the concept of agents in multivariate Markov chains.
Formal approaches to a definition of agents
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.
Neural Coarse-Graining: Extracting slowly-varying latent degrees of freedom with neural networks
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.
Towards information based spatiotemporal patterns as a foundation for agent representation in dynamical systems
We present some arguments why existing methods for representing agents fall short in applications crucial to artificial life.
