Model-Based Closed-Loop Control Algorithm for Stochastic Partial Differential Equation Control
Authors: Peiyan Hu, Haodong Feng, Yue Wang, Zhiming Ma
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct a systematic evaluation of MBCC on two notable SPDEs, showcasing its effectiveness and efficiency. The ablation studies show its ability to handle stochasticity more effectively. |
| Researcher Affiliation | Academia | 1Academy of Mathematics and Systems Science, Chinese Academy of Sciences 2Zhongguancun Academy 3Westlake University EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1 Generation of Regularity Structure Features |
| Open Source Code | Yes | We provide our code in the supplementary materials. |
| Open Datasets | No | The paper describes generating its own datasets based on numerical simulators and previous work, rather than using pre-existing public datasets. For instance: "We first generate the space-time white noise using the numerical simulator as the previous work [Chevyrev et al., 2024]" and "The generation of 2-D space-time white noise and the numerical solver follow [Salvi and Lemercier, 2021]." No specific link or repository for the generated data is provided. |
| Dataset Splits | Yes | As for these models training, we train RF-CNN, CNN, RF-FNO, and FNO with 4000 trajectories, respectively, while testing on 500 trajectories. As for control, we take 4000 trajectories to train the policy net. For the learning of CNN, FNO, RF-CNN, and RF-FNO, we take 400 data, a smaller amount of data, to train and 500 data to test. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as GPU models, CPU models, or memory specifications. It only mentions general experimental setup without hardware information. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers, such as programming languages, libraries, or frameworks. It only implies the use of numerical solvers and neural network backbones without version details. |
| Experiment Setup | Yes | In this setting, we take α = 0.01 and N = 50. In addition, we again train the policy net with 4000 data. On this SPDE, we consider α = 100 and N = 20. The stochasticity of the system is caused by the noise term ξ, we adjust the coefficient σ, which determines the scale of the system s noise. Therefore, we choose a higher σ = 1 and directly test RFCNN and CNN trained with the σ = 0.05 dataset in both Open Loop and Policy Net scenarios again. |