Seminar: Graduate Seminar

ECE Women Community

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Date: May,23,2024 Start Time: 10:30 - 11:30
Location: 1061, Meyer Building
Add to:
Lecturer: Dan Haramati
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:

M.Sc. student under the supervision of Prof. Aviv Tamar.



All Seminars
Skip to content