Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Published: 03 Nov 2023, Last Modified: 27 Nov 2023GCRL WorkshopEveryoneRevisionsBibTeX
Confirmation: I have read and confirm that at least one author will be attending the workshop in person if the submission is accepted
Keywords: deep reinforcement learning, visual reinforcement learning, object-centric, robotic object manipulation, compositional generalization
TL;DR: We introduce a structured visual goal-conditioned RL approach for multi-object manipulation, showcasing agents that generalize from 3 to over 10 objects.
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 objects and their interaction, and use it to learn goal-conditioned manipulation of several objects. Key to our method is the ability to handle goals with dependencies between the objects (e.g., moving objects in a certain order). We further relate our architecture to the generalization capability of the trained agent, and demonstrate agents that learn with 3 objects but generalize to similar tasks with over 10 objects. Rollout videos are available on our website: https://sites.google.com/view/entity-centric-rl
Submission Number: 18