Robotics

Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained …

Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment …

Multimodal pretraining has emerged as an effective strategy for the trinity of goals of representation learning in autonomous robots: …

Learning robust and generalizable control / decision-making policies for robotics and autonomous driving using real-world data.

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of …

H2O introduces a dynamics-aware policy evaluation scheme, which adaptively penalizes the Q function learning on simulated state-action pairs with large dynamics gaps, while also simultaneously allowing learning from a fixed real-world dataset.

Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward …