A Retrospective on Active Inference
Active Inference is a theory of adaptive action selection for agents proposed by Karl Friston initially and now expanded upon by many authors and forms a small academic subfield of research. The core claims of the theory are that action selection and decision-making can be usefully understood as inference problems...
Active Inference is a theory of adaptive action selection for agents proposed by Karl Friston initially and now expanded upon by many authors and forms a small academic subfield of research. The core claims of the theory are that action selection and decision-making can be usefully understood as inference problems (hence the name ‘active’ inference) and that adaptive action can be derived from first principles via the free energy principle, which essentially states that existence of an entity presupposes it performing some approximation to Bayesian inference which includes inference over ‘acti
Explore this link on the map →related reading
- Active Inference and Intentional Behaviourarxiv.org
- Just Ask for Generalization | Eric Jangevjang.com
- Active Inference and the Free Energy Principle - Tasshintasshin.com
- Bayesian Neural Networkscs.toronto.edu
- pdfopenreview.net
- Reward is not the optimization target — LessWronglesswrong.com
- Evolution as Backstop for Reinforcement Learning · Gwern.netgwern.net
- Free energy principle - Wikipediaen.wikipedia.org
- Scaling in the service of reasoning & model-based ML | Yoshua Bengioyoshuabengio.org
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
- Illuminating the Three Dogmas of RL under Evolutionary Light (Mani Hamidi) - Sensorimotor AI Journal Clubsensorimotorai.github.io
- Models Don't "Get Reward" — LessWronglesswrong.com