A Badrinath, Y Flet-Berliac, A Nie… - Advances in Neural …, 2024 - proceedings.neurips.cc
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 …
SG Konan, E Seraj… - Conference on Robot …, 2023 - proceedings.mlr.press
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 …
K Paster, S McIlraith, J Ba - Advances in neural information …, 2022 - proceedings.neurips.cc
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 …
H Liu, P Abbeel - International Conference on Machine …, 2023 - proceedings.mlr.press
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 …