7 citations · 11 across the 13 of their papers we have counts for
16 papers
Generative Value Classifier
Alexander Swerdlow, Perry Dong, Chelsea Finn
Q-learning is premised on learning a function to predict the value of a state-action pair, with the goal of using such a function to guide policy improvement. Most approaches learn…
Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning
Lars Ankile, Perry Dong, Rohan Bhowmik +4
Learning from human demonstrations is a reliable way to teach robots new tasks, but the gains from each additional demonstration shrink as the policy improves. Continued improvemen…
Reinforcement Learning for Real-Time Vision-Language-Action Policies
Perry Dong, Kuo-Han Hung, Dorsa Sadigh +1
Reinforcement learning fine-tuning on top of large, pretrained Vision-Language-Action (VLA) models offers promise for highly reliable robot deployment. However, because of their sc…
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…
Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?
Perry Dong, Ron Polonsky, Dorsa Sadigh +1
Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question:…
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…
FASTER: Value-Guided Sampling for Fast RL
Perry Dong, Alexander Swerdlow, Dorsa Sadigh +1
Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates…
TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
Perry Dong, Kuo-Han Hung, Alexander Swerdlow +2
Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value func…
Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
Andrew Wagenmaker, Perry Dong, Raymond Tsao +2
Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinf…
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…
EXPO: Stable Reinforcement Learning with Expressive Policies
Perry Dong, Qiyang Li, Dorsa Sadigh +1
We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with onlin…
Reinforcement Learning via Implicit Imitation Guidance
Perry Dong, Alec M. Lessing, Annie S. Chen +1
We study the problem of sample efficient reinforcement learning, where prior data such as demonstrations are provided for initialization in lieu of a dense reward signal. A natural…
What Matters for Batch Online Reinforcement Learning in Robotics?
Perry Dong, Suvir Mirchandani, Dorsa Sadigh +1
The ability to learn from large batches of autonomously collected data for policy improvement -- a paradigm we refer to as batch online reinforcement learning -- holds the promise…
Adaptively Learning to Select-Rank in Online Platforms
Jingyuan Wang, Perry Dong, Ying Jin +2
Ranking algorithms are fundamental to various online platforms across e-commerce sites to content streaming services. Our research addresses the challenge of adaptively ranking ite…
RLIF: Interactive Imitation Learning as Reinforcement Learning
Jianlan Luo, Perry Dong, Yuexiang Zhai +2
Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imita…
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning
Jianlan Luo, Perry Dong, Jeffrey Wu +3
The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected…