17 papers
Q-Learning With World Models
Perry Dong, Yueru Jia, Chelsea Finn +1
Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Action models into reliable, high-p…
Improving Robotic Generalist Policies via Flow Reversal Steering
Andy Tang, William Chen, Andrew Wagenmaker +2
Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve on challenging new tasks, we need a way to infer and invoke the appro…
Value Flows
Perry Dong, Chongyi Zheng, Chelsea Finn +2
While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to pr…
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
Yuejiang Liu, Fan Feng, Lingjing Kong +6
General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learn…
EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
Perry Dong, Kuo-Han Hung, Tian Gao +2
The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demonstrated strong generalization a…
Poly-EPO: Training Exploratory Reasoning Models
Ifdita Hasan Orney, Jubayer Ibn Hamid, Shreya S Ramanujam +5
Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time co…