Discrete State-Space Models

Mathematical formalism used in active inference for modeling hierarchical and discrete brain processes.

Neighborhood — ranked by edge-count

framework

Partially Observable Markov Decision Process (POMDP)
associated_with
Modeling framework for discrete state-space decision-making under uncertainty, used as generative model in active inference.

cosine ≥ 0.65 · no typed edge

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

This paper provides a complete mathematical synthesis of active inference on discrete state-space models.claim0.805
Self-description of the paper in the abstract.
In discrete state-space models, agents select from different possible policies to realise their preferences and minimise the surprise that they expect to encounter in the future.claim0.804
Summarises discrete active inference, Section 2.
Discrete Latent Stateconcept0.793
The categorical representation produced by the VAE encoder; used as input to the self-prior and policy networks
Machine Learning-Based State Space Modelingmethod0.792
AI-discovered pathway models that reconstruct decision landscapes and enable prediction of novel interventions in collective decision-making systems.
Diffusion modelsmethod0.761
Generative models that reverse a noising process, mentioned in quasi-simulator table.
Self Modeling Dynamical Systemsframework0.760
Idealized World Model (discrete events)framework0.759
Mathematical formalization of a world with T discrete events and bijective observation functions, used to prove PMI convergence
A system's state and structure encode an implicit and probabilistic model of the environment.claim0.745
Foundational claim about internal representation emerging from free energy optimization.