5 papers
Safe Online Learning via Smooth Safety-Structured Policy Composition
Hongpeng Cao, Liqun Zhao, Yuliang Gu +3
Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches typically rely on either stri…
Real-Time Linear MPC for Quadrotors on SE(3): An Analytical Koopman-based Realization
Santosh M. Rajkumar, Chengyu Yang, Yuliang Gu +3
This letter presents an analytical linear parameter-varying (LPV) representation of quadrotor dynamics utilizing Koopman theory, facilitating computationally efficient linear model…
Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization
Yuliang Gu, Hongpeng Cao, Marco Caccamo +1
Capturing latent variations ("contexts") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control…
Bregman Centroid Guided Cross-Entropy Method
Yuliang Gu, Hongpeng Cao, Marco Caccamo +1
The Cross-Entropy Method (CEM) is a widely adopted trajectory optimizer in model-based reinforcement learning (MBRL), but its unimodal sampling strategy often leads to premature co…
Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control
Sheng Cheng, Ran Tao, Yuliang Gu +3
This paper presents the Task-Parameter Nexus (TPN), a learning-based approach for online determination of the (near-)optimal control parameters of model-based controllers (MBCs) fo…