arXiv subjects

Jinzhu Luo

Publications and source records attributed to Jinzhu Luo.

4 recordsLinked to original sources

arXiv2026

SafeStage: Evaluating Safety Before, During, and After Vision-Language-Conditioned Robot Manipulation

Vision-language-conditioned robot policies integrate perception, language understanding, and control for general-purpose manipulation. However, existing evaluations often focus on task success, isolated physical constraints, semantic refusal, or realized physical damage, providing limited insight into where safety fails during closed-loop manipulation. We introduce SafeStage, a lifecycle-structured benchmark for evaluating manipulation safety before, during, and after task execution. SafeStage contains 97 purpose-built risk scenarios organized into three stages. Initial-State Hazards captures safety-relevant relations that must be resolved before manipulating the target. Execution-Time Safety evaluates unsafe contacts, trajectories, region entries, and object interactions during execution. Final-State Hazards capture unstable or otherwise unsafe conditions remaining after nominal task completion. The benchmark evaluates realized interactions using event-based and state-based checks and reports native task success independently from stage-specific safety outcomes. We evaluate representative direct-action Vision-Language-Action (VLA) policies and policies with world-model-based policies under a common closed-loop protocol. Our results demonstrate that nominal task completion frequently coexists with safety violations and that different policies exhibit distinct failure profiles across the three stages. By separating task success from safety and localizing when violations occur, SafeStage provides a unified diagnostic testbed for evaluating and improving vision-language-conditioned robot manipulation policies.

cs.RO↗

arXiv2025

An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL Subroutines

We take the novel perspective of incorporating offline RL algorithms as subroutines of tabula rasa online RL. This is feasible because an online learning agent can repurpose its historical interactions as offline dataset. We formalize this idea into a framework that accommodates several variants of offline RL incorporation such as final policy recommendation and online fine-tuning. We further introduce convenient techniques to improve its effectiveness in enhancing online learning efficiency. Our extensive and systematic empirical analyses show that 1) the effectiveness of the proposed framework depends strongly on the nature of the task, 2) our proposed techniques greatly enhance its effectiveness, and 3) existing online fine-tuning methods are overall ineffective, calling for more research therein.

cs.LG↗

arXiv2024

Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control

Data augmentation creates new data points by transforming the original ones for a reinforcement learning (RL) agent to learn from, which has been shown to be effective for the objective of improving the data efficiency of RL for continuous control. Prior work towards this objective has been largely restricted to perturbation-based data augmentation where new data points are created by perturbing the original ones, which has been impressively effective for tasks where the RL agent observes control states as images with perturbations including random cropping, shifting, etc. This work focuses on state-based control, where the RL agent can directly observe raw kinematic and task features, and considers an alternative data augmentation applied to these features based on Euclidean symmetries under transformations like rotations. We show that the default state features used in exiting benchmark tasks that are based on joint configurations are not amenable to Euclidean transformations. We therefore advocate using state features based on configurations of the limbs (i.e., the rigid bodies connected by the joints) that instead provide rich augmented data under Euclidean transformations. With minimal hyperparameter tuning, we show this new Euclidean data augmentation strategy significantly improves both data efficiency and asymptotic performance of RL on a wide range of continuous control tasks.

cs.LG↗

arXiv2021

Modeling Multivariate Cyber Risks: Deep Learning Dating Extreme Value Theory

Modeling cyber risks has been an important but challenging task in the domain of cyber security. It is mainly because of the high dimensionality and heavy tails of risk patterns. Those obstacles have hindered the development of statistical modeling of the multivariate cyber risks. In this work, we propose a novel approach for modeling the multivariate cyber risks which relies on the deep learning and extreme value theory. The proposed model not only enjoys the high accurate point predictions via deep learning but also can provide the satisfactory high quantile prediction via extreme value theory. The simulation study shows that the proposed model can model the multivariate cyber risks very well and provide satisfactory prediction performances. The empirical evidence based on real honeypot attack data also shows that the proposed model has very satisfactory prediction performances.

stat.AP↗