4 papers
Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies
Yi Wang, Xinchen Li, Pengwei Xie +13
Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. Deployed robots encounter dist…
Optimal Unpredictable Control for Linear Systems
Chendi Qu, Jianping He, Jialun Li +1
In this paper, we investigate how to achieve the unpredictability against malicious inferences for linear systems. The key idea is to add stochastic control inputs, named as unpred…
IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment
Chenlin Ming, Chendi Qu, Mengzhang Cai +6
Large Language Models (LLMs) have achieved impressive performance through Supervised Fine-tuning (SFT) on diverse instructional datasets. When training on multiple capabilities sim…
3DIOC: Direct Data-Driven Inverse Optimal Control for LTI Systems
Chendi Qu, Jianping He, Xiaoming Duan
This paper addresses the Direct Data-Driven Inverse Optimal Control (3DIOC) problem for linear time-invariant (LTI) systems under the linear quadratic (LQ) control. Unlike traditio…