We present a novel observation about the behavior of offline reinforcement learning (RL)
algorithms: on many benchmark datasets, offline RL can produce well-performing and safe …

We study a new paradigm for sequential decision making, called offline policy learning from
observations (PLfO). Offline PLfO aims to learn policies using datasets with substandard …

Reward-free data is abundant and contains rich prior knowledge of human behaviors, but it
is not well exploited by offline reinforcement learning (RL) algorithms. In this paper, we …

We study offline multitask representation learning in reinforcement learning (RL), where a
learner is provided with an offline dataset from different tasks that share a common …

In offline Imitation Learning (IL), one of the main challenges is the covariate shift between
the expert observations and the actual distribution encountered by the agent, because it is …

Offline preference-based reinforcement learning (PbRL) typically operates in two phases:
first, use human preferences to learn a reward model and annotate rewards for a reward …

Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires
large amounts of data. The challenge arises when labeled datasets are expensive …

We present a novel method, Contextual goal-Oriented Data Augmentation (CODA), which
uses commonly available unlabeled trajectories and context-goal pairs to solve Contextual …

Recent advancements in offline Reinforcement Learning (Offline RL) have led to an
increased focus on methods based on conservative policy updates to address the Out-of …

The reasoning abilities of large language models (LLMs) have improved with chain-of-
thought (CoT) prompting, allowing models to solve complex tasks in a stepwise manner …