Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …

While the conditional sequence modeling with the transformer architecture has
demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is …

Decision transformers recast reinforcement learning as a conditional sequence generation
problem, offering a simple but effective alternative to traditional value or policy-based …

The introduction of Transformers architecture has brought about significant breakthroughs in
Deep Learning (DL), particularly within Natural Language Processing (NLP). Since their …

Preference-based reinforcement learning (PbRL) shows promise in aligning robot behaviors
with human preferences, but its success depends heavily on the accurate modeling of …

As large models become increasingly prevalent, watermarking has emerged as a crucial
technology for copyright protection, authenticity verification, and content tracking. The rise of …

Reinforcement learning (RL), which strives to learn desirable sequential decisions based on
trial-and-error interactions with an unknown environment, has achieved remarkable success …

**化学**(Reinforcement learning, RL) 通过智能体与环境在线交互来学**最优策略,
**年来已成为解决复杂环境下感知决策问题的重要手段. 然而, 在线收集数据的方式可能会引发 …

Abstract Offline Reinforcement Learning (RL) has become a cost-effective data-driven
approach in the realm of Deep Reinforcement Learning, addressing safety and …