cs.LGMar 19, 2026

Authority-Level Priors: An Under-Specified Constraint in Hierarchical Predictive Processing

Authors: Marcy Palejova

Organizations: Anglia Ruskin University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Hierarchical predictive processing explains adaptive behaviour through precision-weighted inference. Explicit belief revision often fails to produce corresponding changes in stress reactivity or autonomic regulation. This asymmetry suggests the framework leaves under-specified a governance-level constraint concerning which identity-level hypotheses regulate autonomic and behavioural control under uncertainty. We introduce Authority-Level Priors (ALPs) as meta-structural constraints defining a regulatory-admissible subset (Hauth, a subset of H) of identity-level hypotheses. ALPs are not additional representational states nor hyperpriors over precision; they constrain which hypotheses are admissible for regulatory control. Precision determines influence conditional on admissibility; ALPs determine admissibility itself. This explains why explicit belief updating modifies representational beliefs while autonomic threat responses remain stable. A computational formalisation restricts policy optimisation to policies generated by authorised hypotheses, yielding testable predictions concerning stress-reactivity dynamics, recovery time constants, compensatory control engagement, and behavioural persistence. Neurobiologically, ALPs manifest through distributed prefrontal arbitration and control networks. The proposal is compatible with variational active inference and introduces no additional inferential operators, instead formalising a boundary condition required for determinate identity-regulation mapping. The model generates falsifiable predictions: governance shifts should produce measurable changes in stress-reactivity curves, recovery dynamics, compensatory cognitive effort, and behavioural change durability. ALPs are advanced as an architectural hypothesis to be evaluated through computational modelling and longitudinal stress-induction paradigms.

Figures & tables

SymbolDefinition
H\mathcal{H}Set of all coherent identity-level hypotheses
Hauth\mathcal{H}_{\text{auth}}Subset of hypotheses authorized for regulatory control
hih_{i}Individual hypothesis (e.g., hsafeh_{\text{safe}} , hthreath_{\text{threat}} )
P(hi∣data)P(h_{i}|\text{data})Posterior probability of hypothesis hih_{i}
πi\pi_{i}Precision (confidence weighting) of hypothesis hih_{i}
CauthC_{\text{auth}}Constraint function determining regulatory admissibility
Table 1: Key symbols and notation used throughout the paper.
Figure 1: Regulatory admissibility architecture. Authority-Level Priors constrain the subset of identity hypotheses permitted to generate policies that interface with autonomic and behavioural regulation. Precision weighting operates only within this authorised subset. This distinction formalises why representational belief updating can occur without corresponding autonomic stabilisation when an adaptive hypothesis remains outside Hauth\mathcal{H}_{\text{auth}} .
More in this topic

Predictive Coding

Predictive coding explains perception and learning through predictions, prediction errors, and updates to internal models.

See all 59 papers

Explore similar work

CardsList
Aug 11, 2026

Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability

Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Barrett and Miller's account of categorization as predictive, compressive, functionally organized, and allostatically constrained, we test whether recurrent and spiking agents develop internal states with corresponding computational properties. Agents operate in an energy-constrained foraging task requiring resource acquisition, threat avoidance, contact-dependent consumption, and regulation of an internal energy variable. In a frozen benchmark, learned agents outperform random and heuristic baselines; the trace-augmented recurrent policy is strongest overall, while spiking variants show stress-specific differences. Early internal dynamics predict later full-safe-efficient success above permutation baseline, reaching a maximum ROC-AUC of 0.802. Reduced PCA subspaces retain behaviorally relevant information. Feature-family controls show that predictive signal is distributed across trace, policy-head, internal-dynamics, observation, and allostatic variables, and low-energy state remains strongly decodable after explicit energy-related features are removed. Evaluation-time perturbations to temporal state, sensory information, operating conditions, and allostatic mechanisms alter behavior and/or internal prediction. Seed-balanced event probes show weaker but measurable information about future contact, successful consumption, and threat events, alongside strong low-energy decoding. We interpret this pattern as a computational analogue of predictive allostatic organization: distributed control regimes that are predictive, energy-sensitive, action-relevant, and partly causally involved, without claiming biological validation or discrete symbolic categories.

Frederick Hayes

Independent Researcher San Antonio, Texas, USA

Partially Observable RLRecurrent Neural NetworksState Representation Learning
AskPDF
Jun 29, 2026

When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency

Adaptive agents are usually judged by what they do, but an agent can appear stable while the internal effort required to keep it stable is increasing. This hidden regulatory burden matters for artificial agents operating under noise, delay, or changing demands: two systems may reach similar internal states while one requires much more corrective control to get there. Here, we study whether that burden depends on history. Using a computational model of adaptive uncertainty regulation, we drive an artificial agent through a continuous change in its uncertainty target and then reverse the change without resetting the agent. This creates a simple test for carryover: does the controller respond only to the current target, or does the path by which the agent reached that target still matter? The simulations show a clear history-dependent effect. The adaptive gain required to regulate the agent forms a reproducible hysteresis loop, meaning that the same target can require different levels of control depending on whether the agent is moving toward or returning from a more demanding regime. The timing of regulation also matters. When stabilization is available before disturbance exposure, the agent generally requires less adaptive gain than when it can only recover after disturbance has already acted. The state-level coherence measure also shows path dependence, but the timing effect is much clearer in regulatory gain. The main difference is therefore not that anticipatory regulation produces a completely different state. Rather, it reaches comparable regulated behavior with lower modeled control demand. These results suggest that adaptive agents should be evaluated not only by whether they remain organized, but by how much regulation they must recruit to do so.

Veronique Ziegler

Independent Researcher

Feedback ControlAdaptive Control
AskPDF
Apr 23, 2026

Dynamical Priors as a Training Objective in Reinforcement Learning

Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as abrupt confidence shifts, oscillations, or degenerate inactivity. We introduce Dynamical Prior Reinforcement Learning (DP-RL), a training framework that augments policy gradient learning with an auxiliary loss derived from external state dynamics that implement evidence accumulation and hysteresis. Without modifying the reward, environment, or policy architecture, this prior shapes the temporal evolution of action probabilities during learning. Across three minimal environments, we show that dynamical priors systematically alter decision trajectories in task-dependent ways, promoting temporally structured behavior that cannot be explained by generic smoothing. These results demonstrate that training objectives alone can control the temporal geometry of decision-making in RL agents.

Sukesh Subaharan

Coimbatore Medical College Coimbatore, TN India

Reinforcement LearningPolicy Gradient MethodsPolicy Learning
AskPDF