Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

arXiv:2404.01220v1 Announce Type: cross
Abstract: Manipulating objects is a hallmark of human intelligence, and an important task in domains such as robotics. In principle, Reinforcement Learning (RL) offers a general approach to learn object manipulation. In practice, however, domains with more than a few objects are difficult for RL agents due to the curse of dimensionality, especially when learning from raw image observations. In this work we propose a structured approach for visual RL that is suitable for representing multiple …

arxiv cs.cv cs.lg cs.ro manipulation object pixels reinforcement reinforcement learning type