We investigate the challenge of parametrizing policies for reinforcement...
Large vision-language models have achieved outstanding performance, but ...
Recent studies on visual reinforcement learning (visual RL) have explore...
Large Language Models (LLMs) significantly benefit from Chain-of-Thought...
We introduce OpenShape, a method for learning multi-modal joint
represen...
Generalizable manipulation skills, which can be composed to tackle
long-...
We study how choices of input point cloud coordinate frames impact learn...
Generalization in deep reinforcement learning over unseen environment
va...
Learning generalizable manipulation skills is central for robots to achi...
Deep Reinforcement Learning (Deep RL) has been receiving increasingly mo...