Deep Parametric Active Inference

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

• Active Inferenceframework0.839
  Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.
• Empathic Active Inferenceframework0.805
  Matsumura et al.'s extension of active inference to include others' welfare in the generative model
• Active inference provides a framework (derived from first principles) for solving and understanding the behavior of autonomous agents.claim0.784
• The key challenge for active inference is finding the generative model that best explains observable data.claim0.784
  Identifies an outstanding problem, Section 10.
• Friston, FitzGerald et al. (2016) — Active inference and learningconcept0.782
  Prior active inference paper providing detailed neurophysiological implementation of belief updates
• Active Inference, Curiosity and Insight (Friston et al., 2017)concept0.778
  The primary source paper being extracted
• Active inference offers an attractive natural adaptation mechanism for non-stationary environments due to its Bayesian model updating properties.claim0.774
  §3, after non-stationary results.
• Millidge 2020: Deep active inference as variational policy gradients (Journal of Mathematical Psychology)concept0.773
  Extends active inference to high-dimensional problems via deep neural network approximations