Can I read Entity-Centric Reinforcement Learning for Object Manipulation from Pixels on EtoBox?

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels by Haramati, Dan; Daniel, Tal; Tamar, Aviv is a scholarly article available to read on EtoBox.

What is Entity-Centric Reinforcement Learning for Object Manipulation from Pixels about?

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, based on a theoretical result for compositional generalization, and demonstrate agents that learn with 3 objects but generalize to similar tasks with over 10 objects. Videos and code are available on the project website: https://sites.google.com/view/entity-centric-rl

Author

Haramati, Dan; Daniel, Tal; Tamar, Aviv

Published

2024

Language

EN