Information-Theoretic Adaptive Cooling for Deterministic MPPI via Entropy Feedback

• URL: http://arxiv.org/abs/2607.14245v1
• Date: Wed, 15 Jul 2026 18:04:38 GMT
• Title: Information-Theoretic Adaptive Cooling for Deterministic MPPI via Entropy Feedback
• Abstract summary: This paper investigates deterministic optimal control using Model Predictive Path Integral (MPPI) control.<n>In deterministic MPPI, the temperature must be driven to zero to recover the true optimum, yet the design of an effective cooling schedule remains a fundamental challenge.<n>We propose an Information-Theoretic Adaptive Cooling (ITAC) framework that uses the Shannon entropy of importance weights as an online feedback signal to regulate the temperature.
• Score: 13.175181677159587
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates deterministic optimal control using Model Predictive Path Integral (MPPI) control, a sampling-based and derivative-free framework well suited for systems with complex dynamics and nonsmooth objectives. In deterministic MPPI, the temperature must be driven to zero to recover the true optimum, yet the design of an effective cooling schedule remains a fundamental challenge. Existing methods typically rely on predefined open-loop schedules, which limit the efficiency and robustness of the algorithm. To overcome this limitation, we propose an Information-Theoretic Adaptive Cooling (ITAC) framework that uses the Shannon entropy of the importance weights as an online feedback signal to regulate the temperature. The proposed mechanism adapts the cooling rate to the current sampling state, enabling fast progress when the weights are diffuse and cautious cooling when they become concentrated. We prove asymptotic convergence of the resulting scheme to the deterministic optimum, and further derive a critical entropy threshold that leads to a smooth barrier against premature weight collapse. Experiments on nonsmooth signal temporal logic motion-planning tasks show that ITAC improves sampling efficiency and achieves substantially faster convergence than state-of-the-art baselines without sacrificing the derivative-free nature of MPPI.

Related papers

• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Sampling-Based Control via Entropy-Regularized Optimal Transport [18.278741443124655]
  OT-MPC is a sampling-based algorithm that overcomes limitations through an entropy-regularized optimal transport formulation.<n>We derive closed-form, gradient-free updates via the Sinkhorn algorithm, enabling real-time performance.
  arXiv  Detail & Related papers  (2026-05-04T02:07:15Z)
• Physics-Informed Machine Learning for Pouch Cell Temperature Estimation [5.435523531334183]
  This paper presents a physics-informed machine learning (PIML) framework for the efficient estimation of steady-state temperature profiles.<n>The PIML approach integrates the governing heat transfer equations directly into the neural network's loss function, enabling high-fidelity predictions.<n>Results demonstrate that the PIML model converges more rapidly and achieves markedly higher accuracy, with a 49.1% reduction in mean squared error over the data-driven model.
  arXiv  Detail & Related papers  (2026-04-16T02:58:10Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• HPTune: Hierarchical Proactive Tuning for Collision-Free Model Predictive Control [55.015741360766945]
  We propose a hierarchical proactive tuning (HPTune) framework that combines both a fast-level tuning and a slow-level tuning.<n>We integrate HPTune with the Doppler LiDAR that provides obstacle velocities apart from position-only measurements for enhanced motion predictions.<n>It is found that HPTune enables situation-tailored motion planning by formulating a safe, agile collision avoidance strategy.
  arXiv  Detail & Related papers  (2026-01-29T07:15:39Z)
• EventFlow: Real-Time Neuromorphic Event-Driven Classification of Two-Phase Boiling Flow Regimes [1.242656043400274]
  Flow boiling is an efficient heat transfer mechanism capable of dissipating high heat loads with minimal temperature variation.<n>Sudden shifts between flow regimes can disrupt thermal performance and system reliability.<n>We propose a real-time framework based on signals from neuromorphic sensors for flow regime classification.
  arXiv  Detail & Related papers  (2025-11-07T18:13:46Z)
• Asymptotically Optimal Change Detection for Unnormalized Pre- and Post-Change Distributions [65.38208224389027]
  This paper addresses the problem of detecting changes when only unnormalized pre- and post-change distributions are accessible.<n>Our approach is based on the estimation of the Cumulative Sum statistics, which is known to produce optimal performance.
  arXiv  Detail & Related papers  (2024-10-18T17:13:29Z)
• Taming Quantum Noise for Efficient Low Temperature Simulations of Open Quantum Systems [4.866728358750297]
  We introduce an effective treatment of quantum noise in frequency space by systematically clustering higher order Matsubara poles equivalent to an optimized rational decomposition. This leads to an elegant extension of the HEOM to arbitrary temperatures and very general reservoirs in combination with efficiency, high accuracy and long-time stability. As one highly non-trivial application, for the sub-ohmic spin-boson model at vanishing temperature the Shiba relation is quantitatively verified which predicts the long-time decay of correlation functions.
  arXiv  Detail & Related papers  (2022-02-08T18:46:11Z)
• Adiabatic Sensing Technique for Optimal Temperature Estimation using Trapped Ions [64.31011847952006]
  We propose an adiabatic method for optimal phonon temperature estimation using trapped ions. The relevant information of the phonon thermal distributions can be transferred to the collective spin-degree of freedom. We show that each of the thermal state probabilities is adiabatically mapped onto the respective collective spin-excitation configuration.
  arXiv  Detail & Related papers  (2020-12-16T12:58:08Z)
• Stochastic Finite State Control of POMDPs with LTL Specifications [14.163899014007647]
  Partially observable Markov decision processes (POMDPs) provide a modeling framework for autonomous decision making under uncertainty. This paper considers the quantitative problem of synthesizing sub-optimal finite state controllers (sFSCs) for POMDPs. We propose a bounded policy algorithm, leading to a controlled growth in sFSC size and an any time algorithm, where the performance of the controller improves with successive iterations.
  arXiv  Detail & Related papers  (2020-01-21T18:10:47Z)
• Time-local optimal control for parameter estimation in the Gaussian regime [68.8204255655161]
  instantaneous control unitaries may be used to mitigate the decrease of information caused by an open dynamics. A possible, locally optimal (in time) choice for such controls is the one that maximises the time-derivative of the quantum Fisher information.
  arXiv  Detail & Related papers  (2020-01-10T16:24:31Z)

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.