7 citations · 11 across the 13 of their papers we have counts for
5 papers · 2 filters
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…
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:…
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…