Learning contact-rich manipulation skills is essential. Such skills require the robots to
interact with the environment with feasible manipulation trajectories and suitable compliance …

Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics
where exploration is risky and expensive. However, it still struggles to acquire skills in …

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 …

Learning effective reinforcement learning (RL) policies to solve real-world complex tasks
can be quite challenging without a high-fidelity simulation environment. In most cases, we …

Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better
policies than the behavior policy used for data collection. However, they face challenges …

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while
satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly …

Deep learning-based trajectory prediction models for autonomous driving often struggle with
generalization to out-of-distribution (OOD) scenarios, sometimes performing worse than …

In this study, we investigate the DIstribution Correction Estimation (DICE) methods, an
important line of work in offline reinforcement learning (RL) and imitation learning (IL). DICE …

Model-based reinforcement learning (RL), which learns environment model from offline
dataset and generates more out-of-distribution model data, has become an effective …

In recent years, offline reinforcement learning (RL) algorithms have gained considerable
attention. However, the role of data sampling techniques in offline RL has been somewhat …