Millidge 2020: Deep active inference as variational policy gradients (Journal of Mathematical Psychology)

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

• Active inference dispenses with the Bellman optimality principle and replaces it with a (variational) principle of least action.claim0.787
  §2, expected free energy section.
• Friston, FitzGerald et al. (2016) — Active inference and learningconcept0.783
  Prior active inference paper providing detailed neurophysiological implementation of belief updates
• Active inference describes the dynamics of systems that persist at non-equilibrium steady-state and that can be statistically segregated from their environment via a Markov blanket.claim0.774
  Sets the theoretical grounding in Section 2.
• Deep Parametric Active Inferencemethod0.773
  Computational method from Sandved-Smith et al. (2021) for modelling metaawareness and attentional control
• Friston, FitzGerald et al. (2017) — Active inference: A process theoryconcept0.770
  Companion paper to which readers are directed for detailed account of active inference scheme
• Active inference offers a degree of plausibility as a process theory of brain function.claim0.768
  Overall assessment from Discussion.
• Active inference treats exploration and exploitation as two different ways of tackling the same problem: minimizing uncertainty.claim0.765
  §2, comment on expected free energy decomposition.
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.764
  §3, after non-stationary results.