Dynamics Models for Offline Hyperparameter Selection in Real-World RL

• URL: http://arxiv.org/abs/2608.11349v1
• Date: Tue, 11 Aug 2026 18:54:51 GMT
• Title: Dynamics Models for Offline Hyperparameter Selection in Real-World RL
• Abstract summary: We present the first application of calibration models in a real-world industrial setting: a municipal water treatment plant.<n>Our results show that these models can generate realistic long-horizon rollouts and recover meaningful hyper parameter sensitivity trends.<n>Overall, our findings provide a proof of concept for using offline dynamics models to support RL deployment in real-world environments.
• Score: 18.05255852818742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A key obstacle to deploying reinforcement learning in real-world systems is hyperparameter selection, particularly when simulators are unavailable and online experimentation is costly. Prior work has proposed calibration models trained on offline data to approximate environment dynamics and enable offline hyperparameter selection, but these methods have so far been evaluated only in simple simulated settings. In this paper, we present the first application of calibration models in a real-world industrial setting: a municipal water treatment plant. We evaluate several calibration model approaches, including a k-nearest neighbors model with a Laplacian distance metric, on high-dimensional, non-stationary sensor data for nexting prediction tasks. Our results show that these models can generate realistic long-horizon rollouts and recover meaningful hyperparameter sensitivity trends. We further examine how calibration models scale to year-long datasets, how they support the selection of fine-tuning learning rates for pre-trained agents, and how robust they are under distribution shift. Overall, our findings provide a proof of concept for using offline dynamics models to support RL deployment in real-world environments, while highlighting important practical challenges for future work.

Related papers

• Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration [88.7332439088792]
  scaling reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs) has emerged as an effective training paradigm.<n>We propose the textbfNonlinear textbfExtrapolation of low-rank trajectories (textbfNExt)<n>Our method reduces computational overhead by approximately 37.5% while remaining compatible with a wide range of RLVR algorithms and tasks.
  arXiv  Detail & Related papers  (2026-04-13T13:28:12Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• Paraformer: Parameterization of Sub-grid Scale Processes Using Transformers [6.622831012413507]
  We propose a "memory-aware" Transformer-based model on ClimSim, the largest dataset ever created for climate parameterization.<n>Our results demonstrate that the proposed model successfully captures the complex non-linear dependencies in the sub-grid scale variables.
  arXiv  Detail & Related papers  (2024-12-21T20:21:52Z)
• SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation [52.6922833948127]
  In this work, we investigate the importance of parameters in pre-trained diffusion models.<n>We propose a novel model fine-tuning method to make full use of these ineffective parameters.<n>Our method enhances the generative capabilities of pre-trained models in downstream applications.
  arXiv  Detail & Related papers  (2024-09-10T16:44:47Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning [52.101643259906915]
  We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations. Existing model-based offline RL methods are not suitable for offline-to-online fine-tuning in high-dimensional domains. We propose an on-policy model-based method that can efficiently reuse prior data through model-based value expansion and policy regularization.
  arXiv  Detail & Related papers  (2024-01-06T21:04:31Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning [25.684201757101267]
  We propose an uncertainty-aware sequence modeling architecture called Environment Transformer. Benefiting from the accurate modeling of the transition dynamics and reward function, Environment Transformer can be combined with arbitrary planning, dynamics programming, or policy optimization algorithms for offline RL.
  arXiv  Detail & Related papers  (2023-03-07T11:26:09Z)
• No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL [28.31529154045046]
  We propose a new approach to tune hyperparameters from offline logs of data. We first learn a model of the environment from the offline data, which we call a calibration model, and then simulate learning in the calibration model. We empirically investigate the method in a variety of settings to identify when it is effective and when it fails.
  arXiv  Detail & Related papers  (2022-05-18T04:26:23Z)
• Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing [2.40966076588569]
  We develop and apply an iterative learning semi-parametric model, with a neural network, to the task of autonomous racing. We show that our model can learn more accurately than a purely parametric model and generalize better than a purely non-parametric model.
  arXiv  Detail & Related papers  (2020-11-17T16:24:10Z)
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment [55.91291559442884]
  This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. We propose to build the notion of continual learning into the modeling process of learning wireless systems. Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2020-11-16T08:24:34Z)
• From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling [2.9897531698031403]
  We propose a differentiable parameter learning framework that efficiently learns a global mapping between inputs and parameters. As training data increases, dPL achieves better performance, more physical coherence, and better generalizability. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods.
  arXiv  Detail & Related papers  (2020-07-30T21:38:56Z)

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.