Reinforcement learning serves as a potent tool for modeling dynamic user interests within
recommender systems, garnering increasing research attention of late. However, a …

In this paper, we present ContExtual Imitation Learning (CEIL), a general and broadly
applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight …

In this work, we decouple the iterative bi-level offline RL (value estimation and policy
extraction) from the offline training phase, forming a non-iterative bi-level paradigm and …

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected and
labeled datasets, which eliminates the time-consuming data collection in online RL …

As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as
sequence modeling that conditions on the hindsight information including returns, goal or …

The capability of continuously learning new skills via a sequence of pre-collected offline
datasets is desired for an agent. However, consecutively learning a sequence of offline tasks …

In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for
offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a …

The connected and autonomous vehicles combined with deep reinforcement learning (DRL)
are capable of handling complex driving scenarios. However, due to the random exploration …

We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies
across different domains with dynamics mismatch. Despite the focus on developing …

Pretrained foundation models have exhibited extraordinary in-context learning performance,
allowing zero-shot generalization to new tasks not encountered during the pretraining. In the …