We investigate the visual cross-embodiment imitation setting, in which agents learn policies
from videos of other agents (such as humans) demonstrating the same task, but with stark …

One of the key reasons for the high sample complexity in reinforcement learning (RL) is the
inability to transfer knowledge from one task to another. In standard multi-task RL settings …

Cross-domain imitation learning studies how to leverage expert demonstrations of one
agent to train an imitation agent with a different embodiment or morphology. Comparing …

Generalizing policies across different domains with dynamics mismatch poses a significant
challenge in reinforcement learning. For example, a robot learns the policy in a simulator …

The burgeoning fields of robot learning and embodied AI have triggered an increasing
demand for large quantities of data. However, collecting sufficient unbiased data from the …

Human motion driven control (HMDC) is an effective approach for generating natural and
compelling robot motions while preserving high-level semantics. However, establishing the …

Aerial robots (drones) offer critical advantages in missions where human participation is
impeded due to hazardous conditions. Among these, search and rescue missions in disaster …

A popular paradigm in robotic learning is to train a policy from scratch for every new robot.
This is not only inefficient but also often impractical for complex robots. In this work, we …

Goal-conditioned reinforcement learning (RL) usually suffers from sparse reward and
inefficient exploration in long-horizon tasks. Planning can find the shortest path to a distant …

The ability to reuse collected data and transfer trained policies between robots could
alleviate the burden of additional data collection and training. While existing approaches …