Legged locomotion has recently achieved remarkable success with the progress of machine
learning techniques, especially deep reinforcement learning (RL). Controllers employing …

Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of
scene understanding and action prediction. Current methods employ both 3D representation …

Cross-domain offline reinforcement learning leverages source domain data with diverse
transition dynamics to alleviate the data requirement for the target domain. However, simply …

Abstract Offline Reinforcement Learning (RL) has shown promising results in learning a task-
specific policy from a fixed dataset. However, successful offline RL often relies heavily on the …

Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning
useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly …

Leveraging the powerful reasoning capabilities of large language models (LLMs), recent
LLM-based robot task planning methods yield promising results. However, they mainly focus …

Deep Reinforcement Learning (DRL) has achieved significant advancements in legged
robot locomotion tasks. However, neural network-based control policies suffer from action …

Humans possess delicate dynamic balance mechanisms that enable them to maintain
stability across diverse terrains and under extreme conditions. However, despite significant …

Offline reinforcement learning (RL) has been widely used in safety-critical domains by
avoiding dangerous and costly online interaction. A significant challenge is addressing …

Adapter-tuning strategy is an efficient method in machine learning that introduces
lightweight and sparse trainable parameters into a pretrained model without altering the …