Abstract This paper introduces Elastic Decision Transformer (EDT), a significant
advancement over the existing Decision Transformer (DT) and its variants. Although DT …

Despite the recent advancements in offline reinforcement learning via supervised learning
(RvS) and the success of the decision transformer (DT) architecture in various domains, DTs …

Transformers, originally devised for natural language processing (NLP), have also produced
significant successes in computer vision (CV). Due to their strong expression power …

Decision Transformers (DT) have drawn upon the success of Transformers by abstracting
Reinforcement Learning as a target-return-conditioned, sequence modeling problem. In our …

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 …

Recently, methods such as Decision Transformer that reduce reinforcement learning to a
prediction task and solve it via supervised learning (RvS) have become popular due to their …

Learning how to act when there are many available actions in each state is a challenging
task for Reinforcement Learning (RL) agents, especially when many of the actions are …

Large transformer models powered by diverse data and model scale have dominated
natural language modeling and computer vision and pushed the frontier of multiple AI areas …

One practical challenge in reinforcement learning (RL) is how to make quick adaptations
when faced with new environments. In this paper, we propose a principled framework for …

While most current research in Reinforcement Learning (RL) focuses on improving the
performance of the algorithms in controlled environments, the use of RL under constraints …