Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration

• URL: http://arxiv.org/abs/2605.07520v1
• Date: Fri, 08 May 2026 09:52:25 GMT
• Title: Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration
• Abstract summary: Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics.<n>We propose ModelDriven Policy Optimization (MDPO), a framework that introduces exploration into differentiable planning by injecting noise into the action space during optimization.
• Score: 2.062593640149623
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However, in highly nonlinear and hybrid discrete-continuous domains, the resulting optimization landscapes are often ill-conditioned, with flat regions and sharp transitions that hinder effective optimization. We propose Model-Driven Policy Optimization (MDPO), a framework that introduces stochastic exploration into differentiable planning by injecting noise into the action space during optimization. Leveraging access to the model, MDPO further adapts the noise magnitude based on gradient-derived sensitivity of the trajectory objective, yielding a time-dependent exploration profile. This enables improved exploration of the objective landscape and helps escape poor local optima via dynamic allocation of exploration across timesteps and iterations. Experiments on benchmark domains demonstrate that MDPO consistently outperforms deterministic differentiable planning, including both the noise-free variant of our method and available state-of-the-art implementations, as well as model-free baselines such as PPO, significantly improving solution quality across challenging nonlinear and hybrid settings. We further analyze the evolution of the adaptive noise magnitude across both time steps and optimization iterations, providing insight into how exploration is allocated during learning.

Related papers

• 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)
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• Dynamic Momentum Recalibration in Online Gradient Learning [6.6375578955686345]
  Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization.<n>In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fixed momentum coefficients inherently distort the balance between bias and variance, leading to skewed or suboptimal parameter updates.<n>We propose SGDF (SGD with Filter), an online, time-varying gain to dynamically refine gradient estimation.
  arXiv  Detail & Related papers  (2026-03-06T10:23:40Z)
• Adaptive Linear Path Model-Based Diffusion [52.84663832658799]
  We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching linear probability path.<n>We also propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions.
  arXiv  Detail & Related papers  (2026-02-02T21:33:03Z)
• TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making [75.29820290660065]
  This paper proposes Thought-Centric Preference Optimization ( TCPO) for effective embodied decision-making.<n>It emphasizes the alignment of the model's intermediate reasoning process, mitigating the problem of model degradation.<n>Experiments in the ALFWorld environment demonstrate an average success rate of 26.67%, achieving a 6% improvement over RL4VLM.
  arXiv  Detail & Related papers  (2025-09-10T11:16:21Z)
• Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization [2.384797824772941]
  We present a comprehensive analysis of DPO's dynamics from a probability evolution perspective.<n>We propose a theoretically grounded bilevel optimization framework that tightly integrate supervised fine-tuning with an enhanced DPO objective a.k.a. stable preference optimization.
  arXiv  Detail & Related papers  (2025-07-10T12:57:39Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Preference-Guided Diffusion for Multi-Objective Offline Optimization [64.08326521234228]
  We propose a preference-guided diffusion model for offline multi-objective optimization.<n>Our guidance is a preference model trained to predict the probability that one design dominates another.<n>Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions.
  arXiv  Detail & Related papers  (2025-03-21T16:49:38Z)
• Nonmyopic Global Optimisation via Approximate Dynamic Programming [14.389086937116582]
  We introduce novel nonmyopic acquisition strategies tailored to IDW- and RBF-based global optimisation.<n>Specifically, we develop dynamic programming-based paradigms, including rollout and multi-step scenario-based optimisation schemes.
  arXiv  Detail & Related papers  (2024-12-06T09:25:00Z)
• Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference [47.460898983429374]
  We introduce an ensemble Kalman filter (EnKF) into the non-mean-field (NMF) variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO) We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-12-10T15:22:30Z)
• Real-Time Optimization Meets Bayesian Optimization and Derivative-Free Optimization: A Tale of Modifier Adaptation [0.0]
  This paper investigates a new class of modifier-adaptation schemes to overcome plant-model mismatch in real-time optimization of uncertain processes. The proposed schemes embed a physical model and rely on trust-region ideas to minimize risk during the exploration. The benefits of using an acquisition function, knowing the process noise level, or specifying a nominal process model are illustrated.
  arXiv  Detail & Related papers  (2020-09-18T12:57:17Z)

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.