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

related reading

• Towards a scale-free theory of intelligent agencymindthefuture.info
• The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
• Active Inference and Intentional Behaviourarxiv.org
• Debugging Reinforcement Learning Systemsandyljones.com
• How can LLM RL Work Despite Information-Theoretic Inefficiencyberen.io
• Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
• State of RL for reasoning LLMs | A. Weersaweers.de
• Irrationality as a Defense Mechanism for Reward-hacking — LessWronglesswrong.com
• Free energy principle - Wikipediaen.wikipedia.org
• The necessity of machine learning theory in mitigating AI riskmishabelkin.substack.com
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewarxiv.org