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

8 results for “Control-as-Inference”

Active Inference or Control as Inference? A Unifying Viewcs.LG

This work frames active inference through control as inference, offering robust control algorithms.

problem Active inference framework lacks practical sensorimotor control algorithms.

method Frame active inference through control as inference, presenting trajectory optimization as inference.

result AI may be framed as partially-observed CaI when the cost function is defined in observation states.

active inference control as inference trajectory optimization probabilistic numerics sensorimotor control

2020-10-01abs ↗pdf ↗

On the Relationship Between Active Inference and Control as Inferencecs.AI

New comparison shows differences in how value is incorporated in AIF and CAI.

problem Clarifying the relationship between Active Inference and Control-as-Inference.

method Formal comparison of AIF and CAI frameworks.

result Primary difference is how value is incorporated into generative models.

Active Inference Control-as-Inference Variational Inference Reinforcement Learning Decision Making

2020-06-23abs ↗pdf ↗

Action-Driven Processes for Continuous-Time Controlstat.ML

Unified reinforcement learning and stochastic processes with action-driven processes.

problem Combining reinforcement learning and stochastic processes for efficient control.

method Action-driven processes, leveraging control-as-inference, and minimizing Kullback-Leibler divergence.

result Action-driven processes unify reinforcement learning and stochastic processes, equivalent to maximum entropy reinforcement learning.

reinforcement learning stochastic processes control-as-inference Kullback-Leibler divergence spiking neural networks

2025-10-30abs ↗pdf ↗

Joint Perception and Control as Inference with an Object-based Implementationcs.LG

Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that…

2019-03-04abs ↗pdf ↗

Risk-sensitive control as inference with Rényi divergencecs.LG

Paper introduces RCaI, a risk-sensitive control method using Rényi divergence.

problem Risk-sensitive control in reinforcement learning.

method RCaI extends CaI using Rényi divergence variational inference.

result Risk-sensitive optimal policy can be obtained by solving a soft Bellman equation.

risk-sensitive control reinforcement learning Rényi divergence variational inference soft Bellman equation

2024-11-04abs ↗pdf ↗

A Unified View of Algorithms for Path Planning Using Probabilistic Inference on Factor Graphscs.LG

Unified approach to path planning using probabilistic inference on factor graphs.

problem Path planning problems using probabilistic inference.

method Unified framework using probabilistic factor graphs and message composition rules.

result Unified approach includes various algorithms like Sum-product, Max-product, Dynamic programming, and mixed criteria.

path planning probabilistic inference factor graphs Active Inference Control as Inference

2021-06-19abs ↗pdf ↗

Reinforcement Learning as Iterative and Amortised Inferencecs.LG

The paper reclassifies RL algorithms using inference concepts.

problem To provide a unified perspective on RL algorithms.

method Using the control as inference framework, the paper classifies RL algorithms as amortised and iterative inference.

result A wide range of RL algorithms can be classified in this new manner.

reinforcement learning inference amortized inference iterative inference control theory

2020-06-13abs ↗pdf ↗

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learningcs.LG

Researchers analyze how algorithmic and implementation choices affect RL performance.

problem Difficulty in separating algorithmic and implementation differences in RL performance.

method Unified derivations through a single control-as-inference objective, categorizing algorithms as EM or KL minimization.

result Implementation details are co-adapted with algorithmic choices, some transferable across algorithms.

Reinforcement Learning Inference-based Actor-Critic MPO AWR

2021-03-31abs ↗pdf ↗