Sophisticated Policies from Epistemic Priors

• URL: http://arxiv.org/abs/2607.19518v1
• Date: Tue, 21 Jul 2026 19:05:52 GMT
• Title: Sophisticated Policies from Epistemic Priors
• Abstract summary: Within a planning horizon, Sophisticated Inference makes active inference closed-loop by allowing future actions to depend on future states and observations.<n>We show that Sophisticated Inference and full-joint-prior active inference solve the environment by combining epistemic drive with closed-loop inference.
• Score: 1.430924337853801
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sophisticated Inference is a variant of active inference often associated with recursive belief modeling and tree search. We argue that its central computational role is simpler: within a planning horizon, it makes active inference closed-loop by allowing future actions to depend on future states and observations. This closed-loop structure can be represented in the epistemic-prior variational free energy framework. Epistemic priors supply the active-inference objective, while a joint posterior over future states and actions supplies the state-contingent control structure. We evaluate this decomposition in the Reactivity Maze, a stochastic benchmark designed to separate epistemic incentive from inner-horizon closed-loop control. The comparison includes three variational objectives with the same state-action posterior family, an action-state factorized active inference objective, Sophisticated Inference, and standard Expected Free Energy planning. The results show that neither ingredient is sufficient on its own. Methods without an epistemic component do not seek information, while methods that prevent future actions from depending on future states cannot turn information into reliable goal-reaching. By contrast, both Sophisticated Inference and full-joint epistemic-prior active inference solve the environment by combining epistemic drive with closed-loop inference. These results show that the advantage associated with Sophisticated Inference need not be specific to tree search itself. It arises from the closed-loop form of active inference, and this form can be represented in epistemic-prior variational inference when the posterior keeps future actions dependent on future states.

Related papers

• Orthogonal JEPA: Factorized Predictive States for Latent World Models [95.20158869896393]
  We introduce method, a latent world-modeling framework based on predictive factorization.<n>We show that method can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure.<n>Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability.
  arXiv  Detail & Related papers  (2026-08-20T13:59:57Z)
• Expected free energy as an information constraint on the Bethe Lagrangian [2.360534864805446]
  Active inference selects actions by minimising an expected free energy functional over predicted futures.<n>We propose an alternative formulation based on a Bethe free energy functional, fully supporting inference by message passing.<n>We show that, as the information demand is varied, the solved multiplier moves through its inactive, interior, and saturated regimes.
  arXiv  Detail & Related papers  (2026-08-17T22:10:54Z)
• Visual Latents Know More Than They Say: Unsilencing Latent Reasoning in MLLMs [54.16324124242172]
  Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models.<n>We identify a previously overlooked optimization pathology in existing latent visual reasoning methods.<n>We show that inference-time latent optimization, without any parameter updates, effectively unleashes the suppressed reasoning capacity of visual latents.
  arXiv  Detail & Related papers  (2026-05-04T15:36:12Z)
• On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation [51.56484100374058]
  We formalise such information-conditioned interaction patterns as behavioural dependency.<n>This induces a probe-relative notion of $$-behavioural equivalence and a within-policy behavioural distance.<n>Results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.
  arXiv  Detail & Related papers  (2026-02-24T22:55:21Z)
• Active Inference in Discrete State Spaces from First Principles [0.0]
  We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle.<n>We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be formulated as constrained divergence minimization problems.
  arXiv  Detail & Related papers  (2025-11-25T13:54:10Z)
• Reframing the Expected Free Energy: Four Formulations and a Unification [3.9121134770873733]
  Active inference is based on the expected free energy. This paper seek to formalize the problem of deriving these formulations from a single root expected free energy definition.
  arXiv  Detail & Related papers  (2024-02-22T11:38:43Z)
• A Semantic Approach to Decidability in Epistemic Planning (Extended Version) [72.77805489645604]
  We use a novel semantic approach to achieve decidability. Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity. We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
  arXiv  Detail & Related papers  (2023-07-28T11:26:26Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Witnessing superpositions of causal orders before the process is completed [0.0]
  What is the most general representation of a quantum state at a single point in time? Can we adapt the current formalisms to situations where the order of quantum operations is coherently or incoherently superposed?
  arXiv  Detail & Related papers  (2022-09-19T16:47:53Z)
• Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker [3.5450828190071655]
  This paper provides a complete mathematical treatment of the active inference framework -- in discrete time and state spaces. We leverage the theoretical connection between active inference and variational message passing. We show that using a fully factorized variational distribution simplifies the expected free energy.
  arXiv  Detail & Related papers  (2021-04-23T19:40:55Z)
• Causal Discovery in Physical Systems from Videos [123.79211190669821]
  Causal discovery is at the core of human cognition. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure.
  arXiv  Detail & Related papers  (2020-07-01T17:29:57Z)
• Sophisticated Inference [8.145323363883234]
  Active inference offers a first principle account of sentient behaviour. It replaces value functions with functionals of (Bayesian) beliefs. In this paper, we consider a sophisticated kind of active inference.
  arXiv  Detail & Related papers  (2020-06-07T11:18:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.