In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL has …
B Kang, X Ma, Y Wang, Y Yue, S Yan - arXiv preprint arXiv:2306.00972, 2023 - arxiv.org
Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on …
A Nie, Y Flet-Berliac, D Jordan… - Advances in …, 2022 - proceedings.neurips.cc
Offline reinforcement learning (RL) can be used to improve future performance by leveraging historical data. There exist many different algorithms for offline RL, and it is well …
Z Zhao, Z Ren, L Yang, F Yuan, P Ren, Z Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Offline reinforcement learning (RL) aims to learn policies from static datasets of previously collected trajectories. Existing methods for offline RL either constrain the learned policy to …
Model-based offline reinforcement learning (RL) algorithms have emerged as a promising paradigm for offline RL. These algorithms usually learn a dynamics model from a static …
Offline methods for reinforcement learning have a potential to help bridge the gap between reinforcement learning research and real-world applications. They make it possible to learn …
W Goo, S Niekum - Conference on Robot Learning, 2022 - proceedings.mlr.press
The goal of offline reinforcement learning (RL) is to find an optimal policy given prerecorded trajectories. Many current approaches customize existing off-policy RL algorithms, especially …
G Li, Y Shan, Z Zhu, T Long, W Zhang - arXiv preprint arXiv:2402.02439, 2024 - arxiv.org
In offline reinforcement learning (RL), the performance of the learned policy highly depends on the quality of offline datasets. However, in many cases, the offline dataset contains very …
Offline methods for reinforcement learning have a potential to help bridge the gap between reinforcement learning research and real-world applications. They make it possible to learn …