6 papers
Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo
Weixin Wang, Yu Yang, Wei Deng +1
We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its weights. Recent Sequential Mon…
Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning
Yu Yang, Yihong Guo, Anqi Liu +1
Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Exi…
MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning
Yihong Guo, Yu Yang, Pan Xu +1
We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods…
Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning
Zhangjie Xia, Yu Yang, Pan Xu
Off-dynamics offline reinforcement learning (RL) aims to learn a policy for a target domain using limited target data and abundant source data collected under different transition…
Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer
Yu Yang, Pan Xu
Decision Transformer (DT) has emerged as a promising class of algorithms in offline reinforcement learning (RL) tasks, leveraging pre-collected datasets and Transformer's capabilit…
How to Provably Improve Return Conditioned Supervised Learning?
Zhishuai Liu, Yu Yang, Ruhan Wang +2
In sequential decision-making problems, Return-Conditioned Supervised Learning (RCSL) has gained increasing recognition for its simplicity and stability in modern decision-making t…