Neural Time-Reversed Generalized Riccati Equation

Authors: Alessandro Betti, Michele Casoni, Marco Gori, Simone Marullo, Stefano Melacci, Matteo Tiezzi

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We support this conjecture by discussing experimental results from a range of optimal control case studies.
Researcher Affiliation Academia Inria, Lab I3S, MAASAI, Universit e Cˆote d Azur, Nice, France, DIISM, University of Siena, Siena, Italy, DINFO, University of Florence, Florence, Italy
Pseudocode No The paper states: 'In appendix B of (Betti et al. 2023) we report a summarizing algorithm of all the procedure presented so far.' This indicates the algorithm is in a separate publication, not directly within this paper.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets No The paper describes generating synthetic data for its experiments (e.g., 'sinusoidal target signal', 'sinusoidal signal') but does not refer to or provide access information for any publicly available or open datasets with proper citations or links.
Dataset Splits No The paper does not specify exact split percentages or sample counts for training, validation, or test datasets, nor does it reference predefined splits with citations.
Hardware Specification Yes All the experiments have been conducted using Python 3.9 with Py Torch 2.0.0 on a Windows 10 Pro OS with an Intel Core i7 CPU and 16GB of memory.
Software Dependencies Yes All the experiments have been conducted using Python 3.9 with Py Torch 2.0.0
Experiment Setup Yes With the choice of τ = 0.5 s, n T = 104 time steps, q = 104, r1 = 103, r2 = 105, we get the results plotted in Fig. 1. The number of iterations for updating the derivatives of the weights of µ is set to niter = 100, with a learning rate λ = 10 5 and a decay factor ε = 103.