Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-
learning (IQL) addresses this by training a Q-function using only dataset actions through a …

Unsupervised pre-training has recently become the bedrock for computer vision and natural
language processing. In reinforcement learning (RL), goal-conditioned RL can potentially …

Reward functions are difficult to design and often hard to align with human intent. Preference-
based Reinforcement Learning (RL) algorithms address these problems by learning reward …

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-
based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution …

Recent advancements in offline reinforcement learning (RL) have underscored the
capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the …

Offline reinforcement learning (RL) has received considerable attention in recent years due
to its attractive capability of learning policies from offline datasets without environmental …

Offline reinforcement learning (RL) presents a promising approach for learning reinforced
policies from offline datasets without the need for costly or unsafe interactions with the …

Combining offline and online reinforcement learning (RL) is crucial for efficient and safe
learning. However, previous approaches treat offline and online learning as separate …

Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining
and online finetuning, promises enhanced sample efficiency and policy performance …

Safe offline RL is a promising way to bypass risky online interactions towards safe policy
learning. Most existing methods only enforce soft constraints, ie, constraining safety …