On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “FEP”

Free Energy Projective Simulation (FEPS): Active inference with interpretabilitycs.AI

FEPS models agents to learn and act in complex environments without deep neural networks.

problem Modeling complex adaptive systems and understanding self-organizing behavior.

method Introducing Free Energy Projective Simulation (FEPS) within the constraints of the free energy principle and active inference.

result FEPS agents resolve ambiguity and infer optimal policies in partially observable environments.

Free Energy Principle Active Inference Interpretability Reinforcement Learning Deep Neural Networks

2024-11-22abs ↗pdf ↗

Targeted free energy estimation via learned mappingsphysics.comp-ph

New method uses neural networks to improve free energy estimation.

problem Estimating free energy differences using FEP is limited by insufficient overlap between distributions.

method Developed a neural network to parameterize a high-dimensional mapping in configuration space.

result Demonstrated substantial variance reduction in free energy estimates.

free energy estimation neural networks machine learning FEP overlap

2020-02-12abs ↗pdf ↗

Realising Synthetic Active Inference Agents, Part II: Variational Message Updatesstat.ML

New algorithm minimizes FE objectives for synthetic AIF agents.

problem Minimizing Free Energy for synthetic active inference agents.

method Variational message passing on Constrained FFGs.

result Message passing algorithms induce epistemic behavior in AIF agents.

Active Inference Free Energy Principle Variational Calculus Factor Graphs Message Passing

2023-06-05abs ↗pdf ↗

Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principlecs.LG

This study proposes hidden state curiosity to enhance RL models' resilience against noise.

problem Curiosity traps in RL models distract agents from discovering novel experiences.

method Proposed hidden state curiosity based on the Free Energy Principle to reward agents for KL divergence between predictive priors and posteriors.

result Agents with hidden state curiosity are more resilient against curiosity traps compared to those with prediction error curiosity.

Reinforcement Learning Curiosity Entropy Prediction Error Free Energy Principle

2024-05-13abs ↗pdf ↗

Active Inference and Epistemic Value in Graphical Modelsstat.ML

This paper introduces a new approach to active inference using constrained Bethe Free Energy.

problem Tackling the limitations of existing epistemic behavior models in active inference.

method Introducing a constrained Bethe Free Energy (CBFE) perspective to optimize epistemic behavior in generative models.

result CBFE optimization leads to more robust and flexible epistemic behavior compared to existing methods.

Active Inference Epistemic Behavior Constrained Bethe Free Energy Message Passing Generative Models

2021-09-01abs ↗pdf ↗

Active Inference for Physical AI Agents -- An Engineering Perspectivestat.ML

AIF improves physical AI agents' performance in dynamic environments.

problem Physical AI agents are less capable than biological agents in open-ended real-world environments.

method Developed from probability theory, Bayesian machine learning, variational inference, and Active Inference (AIF), grounded in the Free Energy Principle.

result AIF minimizes variational free energy and is well-suited to physical constraints.

Active Inference Free Energy Principle Physical AI Reactive Message Passing Variational Inference

2026-03-21abs ↗pdf ↗