5 papers · 1 filter
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
Sarvesh Patil, Mitsuhiko Nakamoto, Manan Agarwal +14
Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-pol…
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…
Flow Q-Learning
Seohong Park, Qiyang Li, Sergey Levine
We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex…
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…
Accelerating Exploration with Unlabeled Prior Data
Qiyang Li, Jason Zhang, Dibya Ghosh +2
Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to solv…