5 papers · 1 filter
Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
Wei Yang, Jiacheng Pang, Shixuan Li +3
Multi-agent systems (MAS) built on Large Language Models (LLMs) are being used to approach complex problems and can surpass single model inference. However, their success hinges on…
Latent Representations for Control Design with Provable Stability and Safety Guarantees
Paul Lutkus, Kaiyuan Wang, Lars Lindemann +1
We initiate a formal study on the use of low-dimensional latent representations of dynamical systems for verifiable control synthesis. Our main goal is to enable the application of…
CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
Anthony Liang, Pavel Czempin, Matthew M. Hong +4
Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation. We study a more practical se…
Integration Matters for Learning PDEs with Backward SDEs
Sungje Park, Stephen Tu
Backward stochastic differential equation (BSDE)-based deep learning methods provide an alternative to Physics-Informed Neural Networks (PINNs) for solving high-dimensional partial…
Data-Driven Reachability with Scenario Optimization and the Holdout Method
Elizabeth Dietrich, Rosalyn Devonport, Stephen Tu +1
Reachability analysis is an important method in providing safety guarantees for systems with unknown or uncertain dynamics. Due to the computational intractability of exact reachab…