quote

active

quote:in-brief-active-inference-proposes-that-agents-achieve-this-by-optimising-two-complementary-objective-functions-a-variational-free-energy-and-an-expected-free-energy

In brief, active inference proposes that agents achieve this by optimising two complementary objective functions, a variational free energy and an expected free energy.

Concise statement of the core hypothesis from Section 2.

Source paper

extracted_from

Active inference on discrete state-spaces: a synthesis

(2020) · Lancelot Da Costa · Thomas Parr · Noor Sajid · Sebastijan Veselic +2

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Active inference postulates that agents achieve survival by optimising two complementary objective functions, a variational free energy and an expected free energy.claim0.929
Core claim of active inference stated in Section 2.
Active inference has no random or stochastic aspects; everything changes to minimize variational free energy in accord with Hamilton's principle of least action.claim0.864
Ontological claim about the deterministic nature of active inference agents in these simulations
Any system that exists will appear to minimize free energy and therefore engage in active inference.claim0.856
The reworked argument that free energy minimization is a corollary of existence, not a prerequisite.
By minimising variational free energy, agents perform approximate Bayesian inference.claim0.851
Describes the epistemic function of variational free energy.
Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.844
Abstract and §3, preference learning section.
Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.claim0.842
§2, comment on expected free energy decomposition.
Active inference dispenses with the Bellman optimality principle and replaces it with a (variational) principle of least action.claim0.838
§2, expected free energy section.
Biological agents use a process theory of active inference where neuronal dynamics correspond to variational free energy minimisation for perception and expected free energy minimisation for action.hypothesis0.837
The core process theory hypothesis set up in the paper.