Publications (17)
ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models
Kejing Wang, Toan Nguyen, Minh Hoang Nguyen +2
Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action polici…
Criticality and Safety Margins for Reinforcement Learning
Alexander Grushin, Walt Woods, Alvaro Velasquez +1
State of the art reinforcement learning methods sometimes encounter unsafe situations. Identifying when these situations occur is of interest both for post-hoc analysis and during…
Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model
Zilong Deng, Simon Khan, Shaofeng Zou
In this work, we study the sample complexity problem of risk-sensitive Reinforcement Learning (RL) with a generative model, where we aim to maximize the Conditional Value at Risk (…
Multi-agent Cooperative Games Using Belief Map Assisted Training
Qinwei Huang, Chen Luo, Alex B. Wu +3
In a multi-agent system, agents share their local observations to gain global situational awareness for decision making and collaboration using a message passing system. When to se…
EMAC+: Embodied Multimodal Agent for Collaborative Planning with VLM+LLM
Shuang Ao, Flora D. Salim, Simon Khan
Although LLMs demonstrate proficiency in several text-based reasoning and planning tasks, their implementation in robotics control is constrained by significant deficiencies: (1) L…
Safety Margins for Reinforcement Learning
Alexander Grushin, Walt Woods, Alvaro Velasquez +1
Any autonomous controller will be unsafe in some situations. The ability to quantitatively identify when these unsafe situations are about to occur is crucial for drawing timely hu…