Active Inference as a Convex Markov Decision Process
Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). In this formulation, the pragmatic terms are linear in the predictive state marginals and therefore equivalent to reward maximization in a latent MDP, while the epistemic value introduces a nonlinear component that distinguishes EFE minimization from sta
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 84%xorbitsai/inference →
“Fuzzy title match (0.92): “Active Inference as a Convex Markov Decision Process” ≈ “xorbitsai/inference””
- LinkedLinked via arxiv author · 85%Nikola Milosevic →
“Active Inference as a Convex Markov Decision Process”
- LinkedLinked via arxiv author · 85%Nicolás Hinrichs →
“Active Inference as a Convex Markov Decision Process”
- LinkedLinked via arxiv author · 85%Nico Scherf →
“Active Inference as a Convex Markov Decision Process”