arXiv:2601. 02754v3 Announce Type: replace-cross Abstract: With the rapid development of e-commerce, auto-bidding has become a key asset in optimizing advertising performance under diverse advertiser environments.
By Mingming Zhang, Na Li, Zhuang Feiqing, Hongyang Zheng, Jiangbing Zhou, Wang Wuyin, Sheng-jie Sun, XiaoWei Chen, Junxiong Zhu, Lixin Zou, Chenliang Li
The paper introduces Q-learning Penalized Transformer (QPT), a training–inference consistent framework for safe offline reinforcement learning. QPT trains a Transformer policy that generates actions conditioned on trajectory context and target return/cost while incorporating a Q-shaped penalty to balance safety, reward maximization, and behavior regularization. The method consistently outperforms strong baselines on 38 DSRL benchmark tasks and adapts robustly to varying constraint thresholds.
arXiv:2608. 15088v1 Announce Type: cross Abstract: Human-in-the-loop (HIL) online reinforcement learning for real robots must absorb human interventions quickly while continuing to improve beyond the human prior.
By Zihang Wang, Yishan Wang
arXiv:2609.34426v2 Announce Type: replace
Abstract: This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an of...
By Shengchao Hu, Peng Wang, Jifeng Hu, Qiyang Zhou, Anning Hu, Li Shen, Ya Zhang, Dacheng Tao
arXiv:2610.19783v1 Announce Type: new
Abstract: Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems su...
By Zhiyuan Zhou, Sergey Levine
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: given a pretrained policy, should the Q-function be pretrained on offline data too? Conventional wisdom suggests it should, but recent results show that online RL with a randomly-initialized Q-function can result in highly performant and reliable policies without needing to pretrain the Q-function.