1 citations · 2 across the 8 of their papers we have counts for
11 papers
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
Zhiyuan Zhou, Andy Peng, Charles Xu +5
Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.…
Any to Full: Prompting Depth Anything for Depth Completion in One Stage
Zhiyuan Zhou, Ruofeng Liu, Taichi Liu +4
Accurate, dense depth estimation is crucial for robotic perception, but commodity sensors often yield sparse or incomplete measurements due to hardware limitations. Existing RGBD-f…
Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging
Yajat Yadav, Zhiyuan Zhou, Andrew Wagenmaker +2
Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act i…
: a VLA That Learns From Experience
Physical Intelligence, Ali Amin, Raichelle Aniceto +53
We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience…
Learning Spatial-Aware Manipulation Ordering
Yuxiang Yan, Zhiyuan Zhou, Xin Gao +5
Manipulation in cluttered environments is challenging due to spatial dependencies among objects, where an improper manipulation order can cause collisions or blocked access. Existi…
Compute-Optimal Scaling for Value-Based Deep RL
Preston Fu, Oleh Rybkin, Zhiyuan Zhou +4
As models grow larger and training them becomes expensive, it becomes increasingly important to scale training recipes not just to larger models and more data, but to do so in a co…
Behavioral Exploration: Learning to Explore via In-Context Adaptation
Andrew Wagenmaker, Zhiyuan Zhou, Sergey Levine
Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to…
Reinforcement Learning with Action Chunking
Qiyang Li, Zhiyuan Zhou, Sergey Levine
We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offl…
AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World
Zhiyuan Zhou, Pranav Atreya, You Liang Tan +2
Scalable and reproducible policy evaluation has been a long-standing challenge in robot learning. Evaluations are critical to assess progress and build better policies, but evaluat…
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
Zhiyuan Zhou, Andy Peng, Qiyang Li +2
The modern paradigm in machine learning involves pre-training on diverse data, followed by task-specific fine-tuning. In reinforcement learning (RL), this translates to learning vi…
Autonomous Improvement of Instruction Following Skills via Foundation Models
Zhiyuan Zhou, Pranav Atreya, Abraham Lee +3
Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly te…