Inferring Structured World Models from Videos

Advances in reinforcement learning have allowed agents to learn a variety of board games and video games at superhuman levels. Unlike humans - which can generalize to a wide range of tasks with very little experience - these algorithms typically need vast number of experience replays to perform at the same level. In this thesis, we propose a model-based reinforcement learning approach that represents the environment using an explicit symbolic model in the form of a domain-specific language (DSL) that represents the world as a set of discrete objects with underlying latent properties that govern their dynamical interactions. We present a novel, neurally guided, on-line inference technique to recover the structured world representation from raw video observations, with the intent to be used for downstream model-based planning. We qualitatively evaluate our inference performance on classical Atari games, as well as on physics-based mobile games.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2022

Author dc:creator

• Kapur, Shreyas

Advisor dc:contributor.advisor

• Tenenbaum, Joshua B.

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright MIT

Licence dc:rights.uri

• http://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/144497

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/144497