While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

Large transformer models trained on diverse datasets have shown a remarkable ability to
learn in-context, achieving high few-shot performance on tasks they were not explicitly …

Recently, diffusion model shines as a promising backbone for the sequence modeling
paradigm in offline reinforcement learning (RL). However, these works mostly lack the …

Large transformer models pretrained on offline reinforcement learning datasets have
demonstrated remarkable in-context reinforcement learning (ICRL) capabilities, where they …

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount
of offline data for complex decision-making tasks. Due to the distribution shift issue, current …

How to extract as much learning signal from each trajectory data has been a key problem in
reinforcement learning (RL), where sample inefficiency has posed serious challenges for …

Active distribution networks are being challenged by frequent and rapid voltage violations
due to renewable energy integration. Conventional model-based voltage control methods …

Reinforcement learning (RL) can in principle let robots automatically adapt to new tasks, but
current RL methods require a large number of trials to accomplish this. In this paper, we …

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to
enhance the agent's generalization ability on unseen tasks. However, the context shift …

Generalization and sample efficiency have been long-standing issues concerning
reinforcement learning, and thus the field of Offline Meta-Reinforcement Learning (OMRL) …