no code implementations • 23 Jan 2024 • Lancelot Da Costa, Samuel Tenka, Dominic Zhao, Noor Sajid
The usefulness of active inference for RL is three-fold.
no code implementations • 22 Dec 2023 • Nathaël Da Costa, Marvin Pförtner, Lancelot Da Costa, Philipp Hennig
While applications of GPs are myriad, a comprehensive understanding of GP sample paths, i. e. the function spaces over which they define a probability measure, is lacking.
no code implementations • 17 Nov 2023 • Karl J. Friston, Lancelot Da Costa, Alexander Tschantz, Alex Kiefer, Tommaso Salvatori, Victorita Neacsu, Magnus Koudahl, Conor Heins, Noor Sajid, Dimitrije Markovic, Thomas Parr, Tim Verbelen, Christopher L Buckley
This paper concerns structure learning or discovery of discrete generative models.
1 code implementation • 2 Jul 2023 • Aswin Paul, Noor Sajid, Lancelot Da Costa, Adeel Razi
Despite being recognized as neurobiologically plausible, active inference faces difficulties when employed to simulate intelligent behaviour in complex environments due to its computational cost and the difficulty of specifying an appropriate target distribution for the agent.
no code implementations • 25 Jul 2022 • Noor Sajid, Panagiotis Tigas, Zafeirios Fountas, Qinghai Guo, Alexey Zakharov, Lancelot Da Costa
These memories are selectively attended to, using attention and gating blocks, to update agent's preferences.
no code implementations • 20 Mar 2022 • Alessandro Barp, Lancelot Da Costa, Guilherme França, Karl Friston, Mark Girolami, Michael I. Jordan, Grigorios A. Pavliotis
In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making.
no code implementations • 22 Nov 2021 • Théophile Champion, Lancelot Da Costa, Howard Bowman, Marek Grześ
In this paper, we present an alternative framework that aims to unify tree search and active inference by casting planning as a structure learning problem.
no code implementations • 21 Sep 2021 • Noor Sajid, Lancelot Da Costa, Thomas Parr, Karl Friston
Conversely, active inference reduces to Bayesian decision theory in the absence of ambiguity and relative risk, i. e., expected utility maximization.
no code implementations • 12 Jul 2021 • Noor Sajid, Francesco Faccio, Lancelot Da Costa, Thomas Parr, Jürgen Schmidhuber, Karl Friston
Under the Bayesian brain hypothesis, behavioural variations can be attributed to different priors over generative model parameters.
no code implementations • 17 Sep 2020 • Lancelot Da Costa, Noor Sajid, Thomas Parr, Karl Friston, Ryan Smith
Precisely, we show the conditions under which active inference produces the optimal solution to the Bellman equation--a formulation that underlies several approaches to model-based reinforcement learning and control.
no code implementations • 7 Jun 2020 • Karl Friston, Lancelot Da Costa, Danijar Hafner, Casper Hesp, Thomas Parr
In this paper, we consider a sophisticated kind of active inference, using a recursive form of expected free energy.
no code implementations • 22 Jan 2020 • Lancelot Da Costa, Thomas Parr, Biswa Sengupta, Karl Friston
We then show that these neuronal dynamics approximate natural gradient descent, a well-known optimisation algorithm from information geometry that follows the steepest descent of the objective in information space.