Reinforcement learning (RL) problems can be challenging without well-shaped rewards.
Prior work on provably efficient RL methods generally proposes to address this issue with …

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 automatic design of soft robots characterizes as jointly optimizing structure and control.
As reinforcement learning is gradually used to optimize control, the time-consuming …

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 …

Soft robots have multiple potential applications for artificial life, ergonomics and human
interaction but they also present many design and control challenges. One of these …

Automatic off-line design is an attractive approach to implementing robot swarms. In this
approach, a designer specifies a mission to be accomplished by the swarm, and an …

The ability to learn from human demonstration endows robots with the ability to automate
various tasks. However, directly learning from human demonstration is challenging since the …

The capability to transfer mastered skills to accomplish a range of similar yet novel tasks is
crucial for intelligent robots. In this work, we introduce $\textit {Diff-Transfer} $, a novel …

The rise of generalist large-scale models in natural language and vision has made us
expect that a massive data-driven approach could achieve broader generalization in other …

We investigate the problem of transferring an expert policy from a source robot to multiple
different robots. To solve this problem, we propose a method named $ Meta $-$ Evolve …