Offline policy learning aims to discover decision-making policies from previously-collected
datasets without additional online interactions with the environment. As the training dataset …

Offline reinforcement learning (RL) aims to learn a policy from pre-collected data, avoiding
costly or risky interactions with the environment. In the offline setting, the inherent problem of …

Abstract Offline Reinforcement Learning (RL) aims at learning effective policies by
leveraging previously collected datasets without further exploration in environments. Model …

Offline reinforcement learning (RL) addresses the problem of learning a performant policy
from a fixed batch of data collected by following some behavior policy. Model-based …

Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …

We consider the problem of learning the best possible policy from a fixed dataset, known as
offline Reinforcement Learning (RL). A common taxonomy of existing offline RL works is …

In offline reinforcement learning (RL), we attempt to learn a control policy from a fixed
dataset of environment interactions. This setting has the potential benefit of allowing us to …

Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from
batch offline data without online interactions with the environment, due to the phenomenon …

In preference-based reinforcement learning (PbRL), a reward function is learned from a type
of human feedback called preference. To expedite preference collection, recent works have …

Offline Reinforcement Learning (RL) aims to extract near-optimal policies from imperfect
offline data without additional environment interactions. Extracting policies from diverse …