7 papers
You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvement
Hang Yu
Coding agents such as Claude Code and Codex close the software loop: a main agent manages the loop, subagents analyze and execute, tools do the work. We port this architecture to r…
Integrating LTL Constraints into PPO for Safe Reinforcement Learning
Maifang Zhang, Hang Yu, Qian Zuo +3
This paper proposes Proximal Policy Optimization with Linear Temporal Logic Constraints (PPO-LTL), a framework that integrates safety constraints written in LTL into PPO for safe r…
CHARM: Considering Human Attributes for Reinforcement Modeling
Qidi Fang, Hang Yu, Shijie Fang +4
Reinforcement Learning from Human Feedback has recently achieved significant success in various fields, and its performance is highly related to feedback quality. While much prior…
How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots
Hang Yu, Qidi Fang, Shijie Fang +2
Enhancing the expressiveness of human teaching is vital for both improving robots' learning from humans and the human-teaching-robot experience. In this work, we characterize and t…
Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations
Shijie Fang, Hang Yu, Qidi Fang +2
Learning from Demonstration (LfD) is a popular approach for robots to acquire new skills, but most LfD methods suffer from imperfections in human demonstrations. Prior work typical…
From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement Learning
Hang Yu, Reuben M. Aronson, Katherine H. Allen +1
Learning from human feedback is an effective way to improve robotic learning in exploration-heavy tasks. Compared to the wide application of binary human feedback, scalar human fee…