Offline reinforcement learning (RL) aims at learning policies from previously collected static
trajectory data without interacting with the real environment. Recent works provide a novel …

Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-
training on a pre-collected dataset with fine-tuning in an online environment. However, the …

We propose a novel model-based offline Reinforcement Learning (RL) framework, called
Adversarial Model for Offline Reinforcement Learning (ARMOR), which can robustly learn …

OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection
of benchmark problems that expose a common interface, and a website where people can …

Policy constraint methods to offline reinforcement learning (RL) typically utilize
parameterization or regularization that constrains the policy to perform actions within the …

Offline reinforcement learning (offline RL), which aims to find an optimal policy from a
previously collected static dataset, bears algorithmic difficulties due to function …

Offline reinforcement learning (RL) algorithms can acquire effective policies by utilizing only
previously collected experience, without any online interaction. While it is widely understood …

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn)
policies in scenarios where the data are collected from a distribution that substantially differs …

Reinforcement learning is known to be sample inefficient, preventing its application to many
real-world problems, especially with high dimensional observations like images …

In offline reinforcement learning (RL), a learner leverages prior logged data to learn a good
policy without interacting with the environment. A major challenge in applying such methods …